JP2020095714A - Automatic manual generation system, automatic manual generation program and automatic manual generation method using AI technology - Google Patents

Abstract

To provide an automatic manual generation system that enables a use of an AI technology to lessen a work burden on an operator.SOLUTION: An automatic manual generation system using an AI technology stores a past database registered in association of past attribute information representing an attribute of a past phone object phoned in the past and a past product proposed in the past with respect to the past phone object with past contract-deal result information indicative of whether a contract comes into effect upon phoning the past phone object in the past and used manual information. An automatic manual generation processing is started in responce to an operation input of an operator. When attribute information on an appointment phone object and product information is input based on a customer list, a selection of a manual based on the input attribute information is performed, manual image data corresponding to a manual screen is generated, an output of the manual is performed based on the generated manual data, and the output manual is registered in the past DB.SELECTED DRAWING: Figure 13

Description

INDUSTRIAL APPLICABILITY The present invention is suitable for application to, for example, a manual automatic generation system, an automatic manual generation program, and a manual automatic generation method using AI technology used in a call center.

2. Description of the Related Art Conventionally, there are known call center companies that perform sales business by telephone, so-called telephone appointments. This call center company makes a call to a call target based on a customer list and product information provided by a product providing company, which is a client (see, for example, Patent Document 1).

JP-A-2005-101812

By the way, when making a call to a scheduled phone call, select and use the manual that matches the phone call, but since the manual is paper-based, you can retrieve the file with the manual sandwiched according to the phone target. However, there is a problem that the operator has to sequentially select the manual by turning over the pages of the file according to the telephone object, and the work burden on the operator is heavy.

The present invention has been made to solve such a problem, and an object thereof is to provide a manual automatic generation system, a manual automatic generation program, and a manual automatic generation method using AI technology capable of reducing the work load of an operator. To do.

In order to solve such a problem, a manual automatic generation system using the AI technique of the present invention is
Past attribute information that represents the past telephone target that has made a telephone call in the past and the attributes of past products that have been proposed in the past for the past telephone target, and the contract when the past telephone target is called in the past. A storage unit that stores a past database in which the past contract information, which is the approval/disapproval of, and the used manual information are registered in association with each other,
An input unit for inputting a scheduled call target to be called and scheduled attribute information indicating attributes of a scheduled contract proposed for the scheduled call target;
A manual selection unit for selecting a manual for the planned telephone object based on the planned attribute information and the past database;
And a display unit for displaying the selected manual.

Further, the manual automatic generation program of the present invention is
To the computer
An input step of inputting a scheduled call target to be called and scheduled attribute information representing attributes of a scheduled contract proposed to the scheduled call target;
Past attribute information that represents the past telephone target that has made a telephone call in the past and the attributes of past products that have been proposed in the past for the past telephone target, and the contract when the past telephone target is called in the past. A manual selection step of selecting a manual for the planned telephone target based on the past database in which the past contract information and the used manual information which are approval/disapproval of the registration are associated and the planned attribute information,
And a display step of displaying the selected manual.

Furthermore, the manual automatic generation program of the present invention includes an input step of inputting a scheduled telephone target to be called and scheduled attribute information representing attributes of a scheduled contract proposed to the scheduled telephone target,
Past attribute information that represents the past telephone target that has made a telephone call in the past and the attributes of past products that have been proposed in the past for the past telephone target, and the contract when the past telephone target is called in the past. A manual selection step of selecting a manual for the planned telephone target based on the past database in which the past contract information and the used manual information which are approval/disapproval of the registration are associated and the planned attribute information,
And a display step of displaying the selected manual.

Further, in the automatic manual generation system using the AI technology of the present invention, a combination of attribute information representing attributes of a telephone object to be called and an item proposed for the telephone object, and a manual identifier for identifying the manual. A storage unit that stores a manual correspondence table registered in association with each other,
An input unit for inputting a scheduled call target to be called and scheduled attribute information indicating attributes of a scheduled contract proposed for the scheduled call target;
A manual selection unit for selecting a manual for the planned telephone object based on the planned attribute information and the past database;
And a display unit for displaying the selected manual.

INDUSTRIAL APPLICABILITY The present invention can realize a manual automatic generation system, an automatic manual generation program, and a manual automatic generation method using AI technology that can utilize owned information.

It is an approximate line figure showing composition (1) of a call center system. It is an approximate line figure showing composition (2) of a call center system. It is a block diagram which shows the structure of a system server. It is an approximate line figure showing composition of an input screen. It is an approximate line figure showing composition of a graph display screen. FIG. 6 is a schematic diagram used to explain designation of search target items. It is a flowchart which shows a contract rate prediction process. It is an approximate line figure showing composition of a telephone sales system. It is a block diagram which shows the structure of an operator terminal. It is an approximate line figure showing composition (1) of a manual screen. It is an approximate line figure showing composition (2) of a manual screen. It is an approximate line figure showing composition (3) of a manual screen. It is a flowchart which shows a manual automatic generation process. FIG. 6 is a schematic diagram used for explanation of selection (1) of an attribute corresponding manual. FIG. 9 is a schematic diagram for explaining selection (2) of an attribute corresponding manual.

Embodiments for carrying out the present invention will be described below with reference to the drawings.

<Overall structure>
Like the call center system 101 shown in FIG. 1, the call center company 103 makes a call to a telephone target designated by the contract from the product providing company 102. At this time, the call center company 103 is provided with the product information in which the information about the customer list and the product which is the list of the scheduled phone calls to be called from the product providing company 102 is described. The customer list includes attribute information, which is a characteristic of the customer, such as the name and telephone number of the telephone target, as well as the gender and age of the telephone target. The product information also includes attribute information that is a characteristic of the product.

The call center company 103 calls the call target 105 based on the customer list and the product information, and proposes a product. As shown in FIG. 2, the call center company 103 supplies contract information to the product providing company 102, which indicates whether or not a contract can be made as a result of making a call. Based on this contract information, the product providing company 102 provides the proposed product to the telephone target 105. The product may be a shaped product or a service.

The call center company 103 extracts attribute information indicating the characteristic of the telephone target from the customer list, but the attribute information indicating the characteristic of the item of the product information, and whether or not the sales contract of the item is possible. Is registered in the past database as past attribute information together with past contract information representing

The call center company 103 performs a contract prediction process based on a past database, such as when there is a new consignment request or consultation of a consignment request from the product providing company 102.

As shown in FIG. 3, in the system server 4 owned by the call center company 103, a control unit 41 including a CPU (Central Processing Unit), a ROM (Read Only Memory) and a RAM (Random Access Memory) is provided in the system server 4. The overall control is performed, and the contract prediction processing and the manual automatic generation processing are executed in accordance with the contract prediction program and the manual automatic generation program stored in advance in the ROM. A past database is stored in the storage unit 45.

In the past database, past attribute information indicating the past call target made a call in the past and the attribute of the past product proposed in the past for the past call target, and a call made in the past to the past call target The reception date and time information at the time of the sale and the past contract information that indicates whether or not the sale and sale of the past product can be established are registered in association with each other. That is, the past attribute information and the past contract information regarding one individual or one individual corresponding information is registered.

The past attribute information is information about the past telephone target, and the attribute information about the telephone target is, for example, the customer type (individual, corporate, trade name of sole proprietor, etc.), gender (male, female, etc.), age. , Phone type (mobile phone, landline phone), initial purchase route (direct mail, web advertisement, introduction of friends, etc.), sleep period (elapsed days since last purchase date, etc.), and number of purchases.

As past attribute information, as information about past products, sales method types (regular purchase products, products purchased each time, etc.) that indicate the types of sales methods, proposal method types that indicate proposal methods (sleeping digging, regular increase, free sample request, etc.) ), a broad product category (health foods, cosmetics, daily necessities, etc.), a detailed product category (green juice, vegetable juice, supplements, basic cosmetics, makeup cosmetics, hair) Dyeing agents, etc., product price range, etc.

The call center company 103 receives the customer list and the product information from a number of product providing companies, and actually makes a call to the call target. Therefore, the call center company 103 holds a large amount of attribute information and contract information (past database) regarding various products. Utilization of this large amount of information (so-called big data) was requested. The present invention is a method of utilizing big data by using AI (artificial intelligence).

<Formation prediction process>
When a request to execute the contract prediction processing is made by the operation input of the administrator via the external interface 43, the control unit 41 of the system server 4 determines the scheduled telephone call target and the scheduled telephone call target to be called. The user is made to input the planned attribute information indicating the attribute of the planned product to be proposed.

For example, as shown in FIG. 4, on the input screen 50, input item columns 51 (51A to 51E) and blanks 52 (52A to 52E) are displayed. The blank 52 has an automatic input method capable of inputting numerical values and a selection input method of selecting one from a pull-down menu, and is set according to an input item. Items of attribute information to be input are displayed in the input item column 51. There is no limit to the number of input item columns 51 and blanks 52 on the input screen 50, and any number can be displayed. It may be entirely contained on one page or may span two or more pages. It is also possible to display more input item columns 51 and blanks 52 in one page by scrolling.

When the control unit 41 recognizes that the input operation is completed according to the operation input of the administrator, the control unit 41 retrieves past attribute information having a value similar to the input value input as the input item according to the similarity extraction condition, and the past attribute is searched. Personalized information corresponding to the information is extracted from the past database. In addition, in this specification, "similar" also includes "perfect match".

The similarity extraction condition is not particularly limited, and it is an input value or a similar range based on the input value for a part of the search target items of the input item (a similar range that is set in advance such as an age of 25 to 30 if 25 years old, A part or all of the input value and the similar range are collectively referred to as an input value range) is searched for in which the past attribute information in the past database is matched. At this time, the extracted individual correspondence information is extracted according to the total number of past attribute information (hereinafter, referred to as match attribute information) that matches the input value range.

For example, the extracted individual correspondence information may be extracted in the descending order of the match attribute information until the predetermined extraction number is reached. Further, the extracted individual correspondence information that matches the input value range may be extracted by a predetermined total number of match attribute information (hereinafter, referred to as a satisfying match number). Further, the number of extracted individual correspondence information may be secured by reducing the number of satisfied matches only when the number of satisfied matches that match the input value range is less than the predetermined number of satisfied extractions.

Further, as the similarity extraction condition, the detection target item may be weighted in advance. For example, the extraction individual correspondence information can be selected from the ones in which the weighting coefficient is set in advance for the detection target item and the total number of weighting coefficients corresponding to the match attribute information is large. The weighting coefficient is stored in the storage unit 45 as a coefficient file in a state of being associated with the search target item, and the control unit 41 reads from the coefficient file and multiplies the weighting coefficient.

Further, the similar extraction conditions can be set in multiple stages (two stages or more). For example, some of the search target items are set as primary search target items, and the rest are set as secondary search target items. The personal correspondence information in which the match attribute information of the primary search target items all match the input value range is set as the population, and according to the total number of match attribute information of the partial search target items that match the input value range of the population, etc. Extracted personalized information is extracted. Of course, it is also possible to use the above-described weighting factors for the primary search target item and the secondary search target item, or to extract the population according to the number of satisfied matches.

Items that have a large impact on the closing rate as primary search target items (customer type, sales method type, proposal method type, product classification, product classification, product price range, etc. ) Is set. In addition, as the secondary search target items, items that have a relatively small effect on the closing rate (dormant period, number of purchases, sex, age, phone type, first purchase route, etc., for example, element items that depend on each phone target) Is set.

Further, the search target item can be changed and the weighting coefficient can be changed according to the input value input to the input item. For example, when “sleep dig up” is selected as the proposal method type, the weighting coefficient of the sleep period, which is the search target item, is increased. This makes it possible to extract a large amount of personalized information having a short dormancy period, and improve the accuracy of the scheduled closing rate.

Further, the control unit 41 can also consider the reception date information in the past contract information as the planned contract rate. The consumption tendency includes not only the age group but also the generational factor. For example, the bubble generation tends to have a high closing rate even in the same age group. Therefore, the new data of the reception date/time information more reflects the current behavior pattern of the age group than the old data. Therefore, the control unit 41 improves the prediction accuracy of the scheduled closing rate by multiplying the date/time weighting coefficient according to the reception date/time information or by preferentially using the corresponding personal information having a new date/time as the reception date/time information. You can

The control unit 41 predicts the planned contract rate based on the past contract information in the extracted individual correspondence information. Specifically, the control unit 41 aggregates the past contract information in the extracted individual corresponding information, calculates the contract rate in the extracted individual corresponding information, and sets this as the planned contract rate. The expected closing rate is calculated by multiplying the expected closing rate by the number of scheduled telephone calls, and the expected sales are calculated by multiplying the expected closing rate by the selling price.

The control unit 41 generates graph display image data for displaying the planned closing rate in a graph based on the calculated planned closing rate, and supplies the graph display image data to the display unit 44. As a result, the graph display screen 60 is displayed on the display unit 44. On the graph display screen 60, a graph 61 showing the closing rate, a sales display column 62 showing the amount of predicted sales, and a search item display column 63 displaying some of the search target items are displayed. .. By thus displaying the graph, the user can understand the expected closing rate at a glance.

As described above, the contract rate prediction program can make a prediction for the planned telephone call target for telephone sales. Here, the call center company 103 in the present embodiment owns big data (a large amount of past attribute information and past contract information) regarding various products and price ranges. Even if the product providing company 102 uses a different price range, different types of products, different customer ages, or different proposal method types, the data provided by the call center company 103 is derived from other companies. The planned closing rate can be calculated using (past attribute information and past closing information). Further, since the call center company 103 owns big data, the bias of the data is small, and it is possible to calculate the scheduled closing rate with high accuracy.

Further, in the closing rate prediction program, it is possible to calculate the planned closing rate by using the customer list, which is a list of scheduled call targets.

For example, the customer list is acquired as data (for example, a spreadsheet file such as a CSV file or an EXCEL file) and stored in the storage unit 45 of the system server 4 via the external interface 43. For example, when entrusting a telephone business for the first time, the items on the customer list may not match the items to be searched. Therefore, the control unit 41 executes the call target list generation process for the customer list in response to the request by the operation input of the administrator, and creates the call target list in accordance with the specification of the self (contract rate prediction program).

Specifically, of the past attribute information to be input, the control unit 41 causes the information regarding the product to be sold to be input by the operation input as described above with reference to FIG. Further, the control unit 41 causes the item corresponding to the search target item to be designated with respect to the information regarding the telephone target to be called. For example, as shown in FIG. 6, the search target item 65 and the customer list are displayed at the same time to specify which column of the customer list corresponds to the search target item 65 (selection from the pull-down list 66 in the figure). If the search target item to be searched does not exist, any value can be input as the value to be used as the search target item.

As a result, the contract prediction program can predict the contract rate by using the schedule attribute information about the call target to be actually called, so that the prediction accuracy can be improved.

It is also possible to combine the contract rate prediction by manually inputting the search target item and the contract rate prediction using the customer list. For example, a simplified version of manual input is published on the WEB site, and the user's contact information is entered in the inquiry form at that time. The call center company 103 can gain a foothold for acquiring new customers by inquiring the contact information. Further, by using the detailed version using the customer list only for the customer, it is possible to add value to the outsourcing of the telephone business.

Next, the contract prediction processing RT1 executed by the control unit 41 of the system server 4 according to the contract prediction program will be described with reference to the flowchart of FIG.

When the control unit 41 of the system server 4 recognizes that the request for executing the contract prediction process is made by the operation input of the administrator or the user, the control unit 41 starts the contract prediction process, and proceeds to step S11.

In step S11, the control unit 41 waits for the input of the schedule attribute information (input target item), and when the schedule attribute information is input, moves to the next step S12.

In step S12, the control unit 41 searches the past database, extracts the individual correspondence information having the past attribute information similar to the input planned attribute information as the extracted individual correspondence information, and proceeds to the next step S13.

In step S13, the control unit 41 totalizes the extracted individual correspondence information, predicts the contract rate for the planned telephone call target, moves to the end step, and ends the process.

<Manual automatic generation process>
Next, a manual automatic generation process that is performed when a call is made to the target of the planned call will be described.

Conventionally, when making a call to a scheduled phone call, the manual is selected and used according to the phone call, but since the manual is paper-based, the file with the manual sandwiched depending on the phone call can be retrieved. However, there is a problem in that the operator must sequentially select the manual by turning over the pages of the file according to the telephone object, which makes the operator complicated to handle.

In the present invention, as shown in the telephone sales system 110 shown in FIG. 8, the system server 4 stores a plurality of manuals, a telephone target list, and a past database. The system server 4 assigns a telephone target to the operator terminal 120 assigned to the operator who makes a call based on the past database and the telephone target list. At this time, the system server 4 causes the operator terminal 120 to display a manual to be used for the assigned telephone target.

As shown in FIG. 9, the operator terminal 120 of the call center company 103 has a control unit 121 of a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The entire system is controlled in a centralized manner, and a manual automatic generation process is executed according to a manual automatic generation program stored in advance in the ROM.

The operator terminal 120 is connected to the system server 4 so as to be able to communicate with each other through a wireless or wired telecommunication circuit. The system server 4 and the operator terminal 120 cooperate to execute the manual automatic generation process. A headset 127 having a microphone and a speaker is connected to each operator terminal 120 so that they can communicate with each other, and a telephone target can be called via the operator terminal 120.

Here, a case will be described in which the storage unit 45 of the system server 4 stores a telephone target list based on the customer list in advance by the telephone target list generation processing described above. It should be noted that there is no limitation on the timing of execution of the telephone list generation process, and it may be executed, for example, before the manual automatic generation process.

The control unit 121 of the operator terminal 120 starts the manual automatic generation process when a start button (not shown) is selected and operated by an operator's operation input via the external interface 123 on a start screen (not shown), for example. The control unit 121 transmits a call target allocation request signal to the system server 4.

The control unit 41 of the system server 4 selects a telephone object to be assigned to the operator terminal 120 (hereinafter, referred to as an assigned telephone object) according to the assignment request signal supplied from the operator terminal 120. Here, the storage unit 45 of the system server 4 stores a plurality of telephone target lists based on the customer lists provided by the plurality of product providing companies 102.

The control unit 41 allocates one or a plurality of telephone target lists to each operator terminal 120 and selects an assigned telephone target from the assigned telephone target list. The control unit 41 uses the scheduled attribute information and the product information associated with the assigned telephone target as items to be notified to the operator as display item information (for example, the name of the assigned telephone target, sex, age, telephone type, etc.). Extract.

Further, the control unit 41 extracts the manual target item referred to when selecting the manual from the planned attribute information and the product information. Here, in the storage unit 45 of the system server 4, a manual correspondence table in which a manual target item and a manual ID (Identification) for identifying the manual are associated with each other is registered. The manual correspondence table is generated based on the past database (details will be described later).

The control unit 41 selects a manual based on the past database by selecting one manual ID from the combination of manual target items. Then, the control unit 41 supplies the display item information and the manual ID to the operator terminal 120, together with the telephone number of the assigned telephone number and the assigned telephone subject ID for identifying the assigned telephone subject.

The storage unit 125 of the operator terminal 120 stores a manual template in advance. The control unit 121 generates manual image data based on the manual and display item information supplied from the system server 4, and displays the manual screen 130 on the display unit 124.

As shown in FIGS. 10 to 12, on the manual screen 130, a display item information column 131 in which display item information is displayed, a start button 132, and manual sentences 133 to 134 and 137 to 138 are displayed. The portion that cannot be displayed on the display unit 124 is indicated by an arrow 135 displayed in response to the operator's scroll operation, indicating that there is a subsequent manual sentence below the displayed screen. Therefore, the operator can visually recognize a part of the attribute information about the assigned telephone target and the manual sentence in advance.

In the manual sentence 133, a conversation sentence when the assigned telephone target answers the telephone is displayed, and in the manual sentences 134 and 137, a plurality of answer sentences corresponding to the responses to the assigned telephone targets are displayed. In the manual sentence 138, a confirmation sentence of the purchase procedure when the assigned telephone target indicates the purchase intention is displayed.

In the manual sentences 133 to 134 and 137 to 138, the display item information is included in the portion where the display item information such as personal information regarding the assigned telephone target such as name and address and the product information such as the name of the product providing company 102 and the product name is entered. It is automatically inserted and displayed. As a result, it is possible to omit the work for the operator to check personal information such as the name and address of the assigned telephone while sequentially collating it with the customer list, and reduce the burden on the operator.

When the start button 132 is operated by the operator, the control unit 121 makes a call to the telephone number to which the assigned telephone is assigned. The operator makes a response while looking at the manual screen 130 displayed on the display unit 124 of the operator terminal 120.

As shown in FIG. 12, on the manual screen 130, a contract button 139A and a non-contract button 139B are displayed. When the operator confirms whether or not the contract can be concluded according to the final judgment of the assigned telephone target, he or she operates either the contract button 139A or the non-contract button 139B depending on whether or not the contract is made.

When the control unit 121 of the operator terminal 120 recognizes that the contract button 139A or the non-contract button 139B has been operated, the control unit 121 generates contract information and associates the manual ID of the manual used with the allocated telephone target ID system. Supply to the server 4.

When the contract information, the manual ID, and the allocated telephone target ID are supplied from the operator terminal 120, the control unit 41 of the system server 4 extracts the attribute information of the allocated telephone target in the telephone target list from the allocated telephone target ID as past attribute information. Then, the contract information and the manual ID are registered in the past database. As a result, in the past database, the attribute information corresponding to the past call target actually called, the contract information, and the used manual ID are registered.

As a result, the system server 4 can continuously add new data (personal correspondence information) to the past database, and the past database can be constructed according to the times.

Therefore, for example, the system server 4 can change various conditions in the closing rate prediction process and the manual automatic generation process according to the latest state of the past database. For example, the weighting coefficient in the past contract information can be recalculated based on the latest contract information in the latest past database to update the coefficient file.

In this way, by automatically selecting and displaying the manual to be used for the assigned telephone target, it is not necessary for the operator to select the manual according to the attribute or product of the telephone target, so the operator's work The burden can be reduced, and the telephone call work of the operator can be made more efficient.

Next, the process of generating the manual correspondence table generated based on the past database will be described. There is no limitation on the timing at which the process of generating the manual correspondence table is performed, and the process may be performed at an arbitrary timing designated by the administrator, or may be periodically performed by a timer setting or the like.

When starting the process of generating the manual correspondence table, the control unit 41 of the system server 4 extracts the manual target item, the contract information, and the manual ID from the past database. The control unit 41 collects contract information for each combination of manual target items and manual ID.

Then, the control unit 41 selects the manual ID having the highest closing rate in the combination of the manual target items, and registers the manual ID for the combination of the manual target items. That is, all combinations of manual target items and manual IDs are registered in the manual correspondence table in association with each other.

The manual correspondence table may be unique to the product when the product providing company 102 specifies a manual, for example. Therefore, a product identification ID for identifying a product is also registered in the past database. In this case, the control unit 41 may execute the manual correspondence table generation process for the individual correspondence information corresponding to the corresponding product identification ID.

For example, when the new product providing company 102 specifies a manual and outsources telephone sales, the sampling method is used. Specifically, a call is made to a part (for example, 5 to 20%) of the customer list while changing the manual for the combination of manual target items. Then, the control unit 41 generates the manual correspondence table by the manual generation process. As a result, an appropriate manual correspondence table can be generated with the first 5 to 20%, and the contract rate can be improved by using an appropriate manual that matches the telephone target. In this case, the data may be registered in the past database or may be registered as another database. The sampling process using this sampling method will be described later in detail.

Next, the contract prediction processing RT2 executed by the control unit 41 of the system server 4 and the control unit 121 of the operator terminal 120 according to the manual automatic generation program will be described with reference to the flowchart of FIG. There is no limitation on the subject of each step, and either the control unit 41 or the control unit 121 executes each step.

In the start step, the manual automatic generation process is started according to the operation input of the operator. In step S20, the attribute information of the planned call target and the product information is input based on the customer list. In step S21, the manual is selected based on the attribute information.

In step S22, manual image data corresponding to the manual screen is generated. In step S23, the manual image data is output as a manual screen.

In step S22, the success/failure information when the call is made and the attribute information of the call target are registered in the past database, and the past database is updated.

Next, the sampling process will be described. The sampling process is executed in parallel with the manual generation process. Note that the manual sentences 133, 136, 138 corresponding to the three display targets of "telephone port correspondence", "personal connection & permission", and "purchase decision" shown in FIGS. Will be omitted.

As shown in FIG. 14, for each of the display targets of “telephone port correspondence”, “personal connection & permission”, and “purchase decision”, a plurality of manual sentences (five in each figure) 133A to 133E, 136A to 136E, 138A to 138E are prepared. This manual sentence 133A to 133E, 136A to 136E, 138A to 138E may be prepared as a common one regardless of a plurality of attribute groups divided by age group and sex, but each attribute group (for example, age It is preferable to prepare a manual sentence suitable for every 5 or 10 years of age, by gender. Of course, part (for example, A to C) may be common and the rest (D, E) may correspond to the attribute group. There is no limit to the number of manual sentences, and it is possible to add them later after checking the closing rate.

The manual sentences A to E are composed of sentences corresponding to respective display objects, and, for example, the politeness and intimacy of the sentences, the degree of explanation about the product, etc. are changed. These manual IDs and manual sentences are registered in the manual correspondence table in an associated state.

As shown in FIG. 15A, for example, on the manual screen 130 corresponding to the telephone port (see FIG. 10), two types of manual sentences 133A and 133B are randomly selected for the telephone target, and one of them is displayed. It That is, when displaying the manual screen 130, the control unit 41 randomly selects one of the manual sentences 133A to 133E stored in the storage unit 45 from the manual sentence selected as the random selection target. , And one of the selected manual sentences 133A or 133B is displayed. Similarly, any one of the manual sentences 136A and 136B and the manual sentences 138A and 138B is displayed.

This random display is executed for a certain number of times for each combination, and the contract rate is totaled for each attribute group. Next, as shown in FIG. 15B, as a result of tabulation, one of the manual sentences 133A having a higher closing rate and the undisplayed manual sentence 133C is randomly selected, and either one is displayed. The display number may be set for each attribute group, or may be set as the total number.

Subsequently, as shown in FIG. 15C, as a result of the aggregation, one of the manual sentence 133A having a higher closing rate and the undisplayed manual sentence 133D is randomly selected, and either one is displayed. The closing rate is totaled for each display target and each attribute group. As a result, among the five types of prepared manual sentences, each one manual sentence 133, 136, 138 corresponding to each attribute group is selected as an attribute corresponding manual sentence. As a result, it is possible to display the optimum manual sentence corresponding to the belonging group on the manual screen 130.

After performing the sampling process for a fixed number of sampling times, the attribute corresponding manual sentence corresponding to each attribute group may be selected each time, and the subsampling process may be subsequently executed.

In this way, by randomly using two manual sentences and repeating selection of the one with a higher closing rate, the number of manual sentences displayed during a certain period is limited to two per one display target. Therefore, compared to the case where three or more types of manual sentences are selected, the displayed manual sentence can be more easily predicted, and the load on the operator can be reduced.

The sub-sampling process is a minor change version of the so-called attribute-adaptive manual sentence in which the expression of endings, wording, or pronunciation method (strong, weak, doubtful, etc.) is slightly changed based on the attribute-supplied manual sentence. By performing the sub-sampling process after the sampling process, the contract rate can be further improved. It should be noted that if there is a result of sampling processing for similar products in advance, it is possible to perform only this sub-sampling processing.

<Second Embodiment>
Next, a second embodiment will be described. The second embodiment is different from the first embodiment in that a manual sentence corresponding to a display target to be displayed next is selected according to a reply from the telephone target. In the second embodiment, the same parts as those in the first embodiment are designated by the same reference numerals and the description thereof will be omitted.

The control unit 41 of the system server 4 determines whether the answer to the call is "favorable", "normal", or "negative" in the display target before product introduction or during product introduction, for example. Specifically, the voice of the telephone object is analyzed, the reply contents are converted into characters, and the voice evaluation point is calculated by analyzing the keyword and the tone of the voice.

For example, when the favorable keywords “always”, “take care of”, “good”, etc. are detected, the control unit 41 analyzes the voice tone of the keyword. The control unit 41 determines that the voice tone is favorable, a "+2" point, determines that the voice tone is average, a "+1" point, and determines that the voice tone is negative, a "0" point. Only add voice evaluation points.

In addition, when the negative keywords such as “oh” and “that” are detected, the control unit 41 analyzes the voice tone of the keyword. The control unit 41 determines that the voice tone is "0" when the voice tone is favorable, the "-1" point when the voice tone is average, and the "-2" when the voice tone is negative. Add only the voice evaluation points.

Further, the control unit 41 compares the voice before the product introduction such as when the personal identification is completed for the first time with the voice of the telephone subject during the product introduction or after the product introduction, and analyzes the change in the tone of the voice. At this time, in order to intentionally give a voice to the telephone target, a sentence requesting a grouping or impression such as "how do you think?" may be inserted in the manual sentence. Then, the control unit 41 only gives a "+5" point if the change in voice before and after the product introduction is favorable, a "0" point if there is no change, and a "-5" point if the change is negative. Add voice evaluation points.

Immediately after the product introduction, the control unit 41 totals the voice evaluation points for the phone-targeted responses. Here, if the voice evaluation score is equal to or higher than the negative threshold value “−2”, the control unit 41 displays the attribute-related manual sentence on the normal process, that is, on the subsequent manual screen 130.

On the other hand, when the voice evaluation score is less than the negative threshold “−2”, the control unit 41 uses the manual sentence for negative evaluation.

Specifically, the system server 4 stores the attribute information and attribute group of the past telephone target, the manual ID of the displayed manual sentence, and the voice evaluation point in association with each other in the storage unit 45. That is, in the past database that is recreated based on the call target list by making a call, the manual ID and voice evaluation score, success/failure information, and attribute group identifier of the manual sentence displayed in addition to the call target list are included. The attribute group ID is recorded.

When the voice evaluation score is a past call target whose score is less than the negative threshold “−2” and the success/failure information is “affirmative”, that is, when the past call target has been closed, the control unit 41 flags the past call target. Stand up. The control unit 41 also totals the attribute groups to which the newly generated past telephone targets belong, selects one combination of the most manual IDs, and sets the combination as the attribute-evaluating manual for negative evaluation.

When the control unit 41 determines that the voice evaluation score is less than the negative threshold value “−2”, the control unit 41 manually sets the manual sentence that is set as the attribute evaluation manual for negative evaluation corresponding to the attribute group of the telephone target. It is displayed on the screen 130.

As described above, by using a manual sentence for negative evaluation, which is different from the normal one, for the telephone target whose voice evaluation score is negative, the contract rate can be further improved.

<Operation and effect>
The features of the invention group extracted from the above-described embodiments will be described below, showing effects and the like as necessary. It should be noted that, in the following, for ease of understanding, the configuration corresponding to each of the above-described embodiments is appropriately shown in parentheses or the like, but is not limited to the specific configuration shown in brackets or the like. The meanings and examples of the terms described in each feature may be applied as the meanings and examples of the terms described in other features described in the same wording.

In the manual automatic generation system (telephone sales system 110) using the AI technology of the present invention, the past attribute indicating the past call target made a call in the past and the attribute of the past product proposed in the past for the past call target. A past database in which information is registered in association with past contract information indicating whether or not the contract can be established when a call is made to the past telephone target in the past, and used manual information (manual ID). A storage unit (storage unit 45) for storing
An input unit for inputting a scheduled call target to be called and scheduled attribute information indicating attributes of a scheduled contract proposed for the scheduled call target;
A manual selection unit for selecting a manual for the planned telephone object based on the planned attribute information and the past database;
And a display unit for displaying the selected manual.

As a result, the manual corresponding to the telephone target is automatically displayed, so that the operator does not have to search for the manual by hand, the burden on the operator can be reduced, and there is no need to manually change the manual. It is also easy to make alternate calls to the telephone targets in the telephone target file. In addition, it is possible to select detailed manuals by utilizing the past database, and it is possible to increase the closing rate of telephone sales.

In the manual automatic generation system using AI technology, the past database is
It is characterized in that the past telephone target and the past product attribute provided by a plurality of contract providing companies are registered.

As a result, since a past database in which a huge number of personalized information items are registered can be used, the result of the contract information can be reflected in the manual selection, and the contract rate of telephone sales can be increased.

The automatic manual generation system using the AI technique is characterized by having an image generation unit that generates a manual image in which a part of the schedule attribute information is fitted to the selected manual.

As a result, the operator does not have to apply the information regarding the telephone object while looking at the manual and talking, so that the workload of the operator can be reduced.

In the automatic manual generation system using AI technology,
The manual selection unit,
Select a manual for the telephone object by a manual correspondence table in which the manual identifier for identifying the manual and the schedule attribute information are registered in association with each other,
The manual correspondence table is
It is generated based on the past database.

As a result, it is possible to select a manual to be used by a simple process of simply searching the schedule correspondence information from the manual correspondence table.

In the automatic manual generation system using AI technology,
It is characterized in that the registration unit stores the scheduled contract attribute and whether the contract is established at the time of making a call to the planned telephone object in the past database.

As a result, the past database can be constantly updated with the latest information, so that it is possible to appropriately link the selection of the manual and the contract information and select the appropriate manual for the telephone target.

In the automatic manual generation system using AI technology,
A storage unit that stores a manual correspondence table that is registered by associating a combination of attribute information that represents an attribute of a product to be called and a target of a call to be made, and a manual identifier that identifies a manual. ,
An input unit for inputting a scheduled call target to be called and scheduled attribute information indicating attributes of a scheduled contract proposed for the scheduled call target;
A manual selection unit for selecting a manual for the planned telephone object based on the planned attribute information and the past database;
And a display unit for displaying the selected manual, the automatic manual generation system using AI technology.

As a result, the manual corresponding to the talk target is automatically displayed, so that the operator does not have to search for the manual by hand and the operator is not burdened with the work load. They can be selected and used in detail and as a result, the closing rate of telephone sales can be increased.

The manual automatic generation system using the AI technology of the present invention has an automatic dialing unit for dialing the communication terminal targeted for the planned call according to an operation input by an operator, and the communication terminal targeted for the call. And

As a result, it is not necessary for the operator to dial, so the load on the operator can be reduced.

The manual selection unit,
After randomly selecting from the two manuals out of the prepared three or more manuals and displaying the selected manual as the selected manual, after displaying a predetermined number of displays,
One of the two manuals having a higher contract rate and one manual selected from the remaining manuals is set as the second manual.

As a result, as a result of comparing the two manuals, the manual with the higher contract rate can be used, and the manual with the highest contract rate is finally selected.

A voice analysis unit (control unit 41) that analyzes the voice of the telephone target;
The manual selection unit,
If the analysis result of the voice is negative,
The voice analysis is characterized by selecting and using a manual for negation.

This makes it possible to use the negation manual when the telephone target voice is negative, so that the contract rate can be improved.

<Other Embodiments>
In the above-described embodiment, the call center company is entrusted with the telephone sales from the product providing company, but this is not necessarily the case. For example, the present invention can be used in a company that provides products and has its own call center. Even in this case, the effect of the present invention is similar to that of the above-described embodiment.

In the above-described embodiment, the manual correspondence table is generated based on the past database, but this is not the only option. Even in this case, it is possible to obtain the same effect as the above-described embodiment that the work load on the operator can be reduced.

Although the manual correspondence table is used in the above-described embodiment, it is not limited thereto. For example, the past database may be searched for each telephone target and the manual with the highest closing rate may be selected.

In the above-described embodiment, the system server 4 is configured to perform manual selection, but this is not the only option. For example, the manual correspondence table may be stored in the operator terminal 120, and the operator terminal 120 may perform the manual selection.

In the above-described embodiment, the display item information is displayed by being embedded in the manual sentence, but it is not limited to this. For example, a symbol may be displayed in the inset portion of the manual sentence, and the display item information may be displayed in a fixed state at the top.

In the above-described embodiment, the system server 4 allocates the telephone objects, but this is not the only option. For example, attribute information and telephone numbers related to a telephone target may be collectively supplied to a plurality of persons, and the operator terminal may select and allocate the telephone target.

In the above-described embodiment, the manual image that has already been created is selected and the manual image data is generated by fitting only the display item information, but the present invention is not limited to this. For example, a talk ID is attached to each manual sentence used as a manual screen, and is registered in the past database as a manual identifier. It is also possible to select a talk ID having a high contract rate for each combination of attribute information by collecting the past database and combine them to generate a manual image.

Conventionally, the talk manual was created by the person in charge, and since the creator's thoughts and feelings were included in it, it was not known before the start of use whether or not the talk manual was suitable for the outcome. In addition, it takes a lot of man-hours and time to create the manual, and the labor of the person in charge is great.

As a result, by automatic generation using AI technology that utilizes big data, it is possible to create a manual that has higher accuracy and leads to results than conventional manual manual creation.
In addition, the labor required for preparation is significantly reduced, which makes it possible to improve labor productivity.

In the above-described embodiment, one manual sentence is displayed by randomly selecting from two manual sentences in the sampling process, but may be randomly selected from three or more manual sentences.

In the above-described embodiment, as the voice analysis, the change of the keyword, the voice tone of the keyword, and the voice tone before the product introduction or during the product description or after the product introduction is analyzed, but at least one of them may be used as the voice analysis. ..

In the above-mentioned embodiment, when the analysis result of the voice is negative, the voice analysis selects and uses a manual for negation. However, for example, the voice evaluation score as the result of the voice analysis is scored. Alternatively, the manual corresponding to the belonging group corresponding to the classified voice evaluation point group may be used. It is also possible to use different manuals for each keyword issued by the telephone object.

The present invention can be applied to, for example, a call center that conducts telephone sales.

4: System server 41, 121: Control unit 43, 123: External interface 44, 124: Display unit 45, 125: Storage unit 50: Input screen 51: Input item column 52: Blank 60: Graph display screen 61: Graph 62: Sales display column 63: Search item display column 65: Search target item 66: Pull-down list 101: Call center system 102: Product providing company 103: Call center company 105: Telephone target 110: Telephone sales system 120: Operator terminal 127: Headset 130 : Manual screen 131: Display item information column 132: Start button 133, 134, 137, 138: Manual sentence 135: Arrow 139A: Close button 139B: Non-close button

Claims (11)

Past attribute information that represents the past telephone target that has made a telephone call in the past and the attributes of past products that have been proposed in the past for the past telephone target, and the contract when the past telephone target is called in the past. A storage unit that stores a past database in which the past contract information, which is the approval/disapproval of, and the used manual information are registered in association with each other,
An input unit for inputting a scheduled call target to be called and scheduled attribute information indicating attributes of a scheduled contract proposed for the scheduled call target;
A manual selection unit for selecting a manual for the planned telephone object based on the planned attribute information and the past database;
A display unit for displaying the selected manual,

An automatic manual generation system using AI technology, characterized by comprising: The past database is
The past automatic call target and the past product attribute provided by a plurality of contract providing companies are registered. The automatic manual generation apparatus using the AI technology according to claim 1, wherein. For the selected manual,
An image generation unit that generates a manual image in which a part of the schedule attribute information is embedded,
A manual automatic generation system using the AI technology according to any one of claims 1 to 2. The manual selection unit,
Select a manual for the telephone object by a manual correspondence table in which the manual identifier for identifying the manual and the schedule attribute information are registered in association with each other,
The manual correspondence table is
It is generated based on the past database. The automatic manual generation system using the AI technology according to any one of claims 1 to 3. The registration unit that stores the planned contract attribute and whether or not the contract is established when the user makes a call to the planned call target in the past database. Manual automatic generation system using AI technology. The manual selection unit,
After randomly selecting from the two manuals out of the prepared three or more manuals and displaying the selected manual as the selected manual, after displaying a predetermined number of displays,
The manual using the AI technology according to claim 1, wherein one of the manuals having a higher contract rate among the two manuals and one manual selected from the remaining manuals are the manuals. Automatic generation system. A voice analysis unit for analyzing the voice of the telephone target,
The manual selection unit,
If the analysis result of the voice is negative,
The automatic manual generation system using the AI technology according to claim 1, wherein a manual for denial of voice analysis is selected and used. An automatic dial unit for dialing the communication terminal targeted for the planned telephone call according to an operator's operation input,
The manual automatic generation device using the AI technology according to claim 1, further comprising: the communication terminal for the telephone call. To the computer
An input step of inputting a scheduled call target to be called and scheduled attribute information representing attributes of a scheduled contract proposed to the scheduled call target;
Past attribute information that represents the past telephone target that has made a telephone call in the past and the attributes of past products that have been proposed in the past for the past telephone target, and the contract when the past telephone target is called in the past. A manual selection step of selecting a manual for the planned telephone target based on the past database in which the past contract information and the used manual information which are approval/disapproval of the registration are associated and the planned attribute information,
And a display step of displaying the selected manual, the automatic manual generation program using AI technology. An input step of inputting a scheduled call target to be called and scheduled attribute information representing attributes of a scheduled contract proposed to the scheduled call target;
Past attribute information that represents the past telephone target that has made a telephone call in the past and the attributes of past products that have been proposed in the past for the past telephone target, and the contract when the past telephone target is called in the past. A manual selection step of selecting a manual for the planned telephone target based on the past database in which the past contract information and the used manual information which are approval/disapproval of the registration are associated and the planned attribute information,
And a display step of displaying the selected manual, the automatic manual generation program using AI technology. A storage unit that stores a manual correspondence table that is registered by associating a combination of attribute information that represents an attribute of a product to be called and a target of a call to be made, and a manual identifier that identifies a manual. ,
An input unit for inputting a scheduled call target to be called and scheduled attribute information indicating attributes of a scheduled contract proposed for the scheduled call target;
A manual selection unit for selecting a manual for the planned telephone object based on the planned attribute information and the past database;
And a display unit for displaying the selected manual, the automatic manual generation system using AI technology.

Images