Information processing device, information processing method, and information processing program

Abstract

Provided are an information processing device, an information processing method, and an information processing program with which it is possible to accurately extract a related program for predicting the audience rating of a target program. An information processing device (30) according to one embodiment of the present disclosure is provided with an acquisition unit (31), an extraction unit (32), and a prediction unit (33). An acquisition unit (31) acquires previous programs that are candidates for related programs used for rating prediction of a target program. An extraction unit (32) extracts a related program from the past programs on the basis of the broadcast and television stations, the playback date and time, the program name, and the program content of the past programs. A prediction unit (33) predicts the audience rating of the target program by using the related program.

Description

Technical Field

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. Background Art

[0002] For example, Patent Document 1 describes an advertisement slot optimization system for optimizing advertisement slots played in broadcast media. The advertisement slot optimization system includes a high-level ratings prediction device (SHARE). The high-level ratings prediction device (SHARE) is configured to predict target ratings with a higher accuracy than a prescribed accuracy, and / or input ratings data measured in real time by a third-party organization, and send the predicted ratings data of the advertisement slot and / or the ratings data before it is played to a target actual optimization device (TAOS).

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: International Publication No. 2018 / 131576 Summary of the invention

[0006] Problems to be solved by the invention

[0007] However, the conventional techniques including Patent Document 1 have room for improvement in terms of accurately extracting related programs for use in predicting the audience rating of a target program.

[0008] Therefore, one of the objects of the present disclosure is to provide an information processing device, an information processing method, and an information processing program capable of extracting related programs for use in ratings prediction of a target program with high accuracy.

[0009] Technical solutions to solve problems

[0010] An information processing device according to one embodiment of the present invention is characterized in that it comprises: an acquisition unit which acquires past programs that are candidates for related programs for predicting the ratings of a target program; and an extraction unit which extracts the related programs from the past programs based on the broadcasting station, broadcast date and time, program name, and program content of the past programs.

[0011] Effects of the Invention

[0012] According to one aspect of the present disclosure, there can be provided an information processing device, an information processing method, and an information processing program capable of extracting a related program for use in ratings prediction of a target program with high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a diagram showing an example of a schematic configuration of a system including an information processing device (audience rating prediction device).

[0014] Figure 2 This is a functional block diagram showing an example of the internal structure of an information processing device (audience rating prediction device).

[0015] Figure 3 This is a diagram showing an example of extraction of related programs based on edit distance.

[0016] Figure 4 This is a diagram showing an example of extracting related programs based on the broadcasting station, broadcast date, start time, end time, and program name of the target program and previous programs.

[0017] Figure 5 is a diagram showing a first example of extraction of related programs based on BERT.

[0018] Figure 6 is a diagram showing a second example of extraction of related programs based on BERT.

[0019] Figure 7 This is a diagram showing an example of the functional structure of a cost calculation device, a broadcast distribution device, and an information processing device (audience rating prediction device).

[0020] Figure 8 This is a diagram showing an example of the hardware configuration of a cost calculation device, a broadcast distribution device, and an information processing device (audience rating prediction device). DETAILED DESCRIPTION

[0021] For example, in television broadcasts, commercials (CMs) are broadcast as advertisements. In television commercials, messages are repeatedly delivered through sound and images, which can leave an impression of products, services, etc. on the audience.

[0022] Television commercials are usually distributed through media time transactions in which advertising companies sell media time slots provided by television stations as media companies to advertisers. Television commercials are roughly divided into timed commercials (time CM) and spot commercials (spot CM).

[0023] Scheduled commercials are commercials that advertisers broadcast during program time (commercials broadcast during time slots bought and sold together with programs) in exchange for paying program production costs. Scheduled commercials may be referred to as program ads, program commercials, sponsored commercials, and the like.

[0024] Commercial breaks are commercials that are not provided with programs and are mainly broadcast between programs (commercials broadcast during the commercial time period specified by the TV station). Commercial breaks are divided into station breaks (SB) broadcast between programs, and participations (PT) inserted into programs but not displayed (or joint commercials).

[0025] Here, the cost calculation of TV commercials is performed using a calculation formula that includes the ratings (predicted ratings) of the target program. For example, commercial inserts are planned in units of gross rating points (GRP). The cost per 1GRP is called the rating point cost. Usually, the rating point cost is different for each delivery mode (such as inverted L-shaped, all-day type, ヨ-shaped, U-shaped, straight-shaped, late-night type, all-day daytime type, etc.). If a delivery mode is selected, the cost of commercial inserts can be calculated based on GRP×rating point cost.

[0026] In addition, the predicted ratings of the target program are obtained by using the ratings of related programs associated with the target program (for example, the broadcasts before the previous episode of a series, the broadcasts before the previous episode of a special program, etc.). Therefore, in order to accurately extract related programs for predicting the ratings of the target program, the inventors conceived an information processing device (ratings prediction device) having the following structure.

[0027] That is, an information processing device (ratings prediction device) of one embodiment of the present invention comprises: an acquisition unit, which acquires previous programs that are candidates for related programs for ratings prediction of a target program; and an extraction unit, which extracts related programs from the previous programs based on the broadcasting station, broadcast date and time, program name, and program content of the previous programs.

[0028] Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the following description, the same symbols are marked on the same parts. Since the names, functions, etc. of the same parts are the same, the detailed description will not be repeated.

[0029] Figure 1 1 is a diagram showing an example of a schematic configuration of a system including an information processing device (audience rating prediction device) of one embodiment. The system 1 includes a cost calculation device 10, a broadcast distribution device 20, and an information processing device (audience rating prediction device, audience rating management device) 30. The cost calculation device 10, the broadcast distribution device 20, and the information processing device 30 are connected to each other via a network 40 so as to be communicable therewith.

[0030] The cost calculation device 10 calculates the cost of a television commercial, for example. The cost calculation device 10 calculates the cost of a television commercial based on a calculation formula including the audience rating (predicted audience rating) of a target program in which the television commercial is inserted.

[0031] The cost calculation device 10, for example, obtains the cost of each commercial insertion pattern within a specified period (e.g., one week) of a certain broadcasting and television station (also read as a channel). Here, the cost in the present disclosure may represent the cost per rating point (Cost Per Rating) of the fee per 1GRP (1%) of the rating. The delivery pattern may include existing (arbitrary) delivery patterns (e.g., inverted L-shaped, all-day type, ヨ-shaped, U-shaped, straight-shaped, late-night type, all-day daytime type, etc.). In addition, the cost calculation device 10 may also obtain the cost of each delivery pattern, the time period constituting the delivery pattern, etc. based on input from the outside (e.g., the settings of the broadcasting and television station).

[0032] The cost calculation device 10 may also obtain (e.g., receive) information used for cost calculation. For example, the cost calculation device 10 may obtain (receive) information about the ratings of each advertising spot from the information processing device 30 (e.g., household ratings, personal ratings, personal overall ratings, and ratings obtained by adding real-time viewing and time-shifted viewing until the 7th day after broadcasting (may also be referred to as "All&P+C7 (Program+Commercial7)", etc.). The cost calculation device 10 may also derive the cost of 1 time slot at A time based on the setting of 1 unit price at A time of the broadcasting station and the information about the ratings obtained from the information processing device 30. Here, "the information about the ratings obtained from the information processing device 30" may be equivalent to "the ratings (predicted ratings) of the target program where the TV commercial is inserted".

[0033] The cost calculation device 10 may be a portable terminal (mobile communication terminal) such as a mobile phone, a smart phone, or a tablet terminal, or may be a fixed communication terminal such as a personal computer (PC) or a server. That is, the cost calculation device 10 in the present disclosure may be read as a communication device. In addition, the cost calculation device 10 may communicate with a network (such as the Internet) via wired and / or wireless (for example, LTE (Long Term Evolution), NR (New Radio), Wi-Fi (registered trademark), etc.).

[0034] The broadcast distribution device 20 is a device for distributing broadcasts to televisions (TV). Here, the television (television receiver) may be a device having at least one function of receiving terrestrial broadcasts, broadcasts from broadcasting satellites (BS: Broadcasting Satellite) / communications satellites (CS: Communications Satellite), Internet broadcasts (Internet TV), etc. For example, the television may be a multi-function TV, a smart TV, an IP (Internet Protocol) TV, a set-top box, etc. In addition, broadcasting refers to the transmission of telecommunications for the purpose of direct reception by the public, and may also include wireless broadcasts, Internet broadcasts, etc.

[0035] The information processing device 30 is a device for collecting statistics on the actual ratings of programs broadcast on television. In addition, the information processing device 30 is a device for predicting the ratings of programs (target programs) to be broadcast on television. The ratings can be stored in a specified time unit (e.g., seconds, minutes, hours). The information processing device 30 can send information about the ratings (e.g., the ratings of the target program inserted in the television commercial (predicted ratings)) to another device (e.g., the cost calculation device 10) via a network.

[0036] The information processing device 30 may be, for example, a device managed by a television ratings investigator. The information processing device 30 may obtain and manage viewing history data from a measuring device of a television connected to a specified household (for example, a survey cooperative household). In addition, the ratings may also be calculated or predicted based on the data. The information processing device 30 may record the ratings of each specified target (a user who meets the specified attributes) (the target's personal ratings). In addition, in the present disclosure, it is assumed that the target is a gender and age classification used in the marketing field (children (C: Child) group, teenagers (T: Teen) group, male (M: Male) 1-M3 group, female (F: Female) 1-F3 group), but is not limited to this classification.

[0037] The information processing device 30 is configured to be able to predict the "audience's advertising ratings" of television with high accuracy by using a new analysis method such as processing big data. The information processing device 30 may include: a data input unit that inputs data source information; an explanation variable conversion unit that performs specific processing on the data source information input from the data input unit to explain the data source information; a program installation / execution unit that installs a program of a prescribed algorithm; and a data output unit that outputs the result of the program installation / execution unit. The algorithm of the program installed by the program installation / execution unit is executed using the data source information input from the data input unit and the explanation variables obtained by the explanation variable conversion by the explanation variable conversion unit, and the predicted ratings data obtained by executing the algorithm is output from the output unit. Based on the output predicted ratings data, the advertising position can be optimized. Here, as the data source information for calculating the ratings (predicted ratings) of the target program for inserting a television commercial, the ratings of related programs related to the target program (for example, the broadcast before the previous episode of a series, the broadcast before the previous special program, etc.) can be used.

[0038] In addition, the system structure is an example and is not limited to this. For example, each device Figure 1 The system 1 may include one each, but the number of each device is not limited thereto and may include multiple devices. The system 1 may include a structure that does not include some devices, or may include a structure that implements the function of one device through multiple devices. Conversely, a structure in which one device implements the functions of multiple devices may be adopted. For example, at least two of the cost calculation device 10, the broadcast distribution device 20, and the information processing device 30 may be installed on one server.

[0039] Figure 2 This is a functional block diagram showing an example of the internal configuration of the information processing device (audience rating prediction device) 30. The information processing device 30 includes an acquisition unit 31, an extraction unit 32, and a prediction unit 33. The information processing method and information processing program disclosed herein are implemented by causing a computer included in the information processing device 30 (acquisition unit 31, extraction unit 32, and prediction unit 33) to execute prescribed processing steps.

[0040] The acquisition unit 31 acquires past programs that are candidates for related programs used for audience rating prediction of the target program. The acquisition unit 31 is not limited in time or content, and can acquire all past programs that are candidates for related programs.

[0041] The extraction unit 32 narrows down the past programs acquired by the acquisition unit 31 to the programs broadcasted before the specified period of the broadcast date and time of the target program, and extracts them. For example, when the predicted audience ratings of the target program are to be calculated three days before the broadcast date, the extraction unit 32 narrows down the past programs broadcasted before four days before the broadcast date of the target program. In addition, when the system is installed, all past programs that can be acquired at the prediction time can be used. In addition, there is a degree of freedom regarding the period for calculating the predicted audience rating of the target program, and various design changes can be made. Furthermore, it is also possible not to narrow down the past programs corresponding to the period for calculating the predicted audience rating of the target program.

[0042] The extraction unit 32 extracts related programs for the target program's ratings prediction from the previous programs based on the previous program's broadcasting station, broadcast date and time, program name, and program content. The previous program's broadcasting station, broadcast date and time, program name, and program content can be obtained from, for example, VR program information that has been databased with the program name, broadcast minutes, broadcast start time, broadcast day, and broadcast station name after the OA is finished from a video survey. In addition, the previous program's broadcasting station, broadcast date and time, program name, and program content can be obtained from, for example, TV metadata, a database that records and produces the actual broadcast content of the companies or products, stores, music, performers, etc. introduced in the program through a unique input interface after the OA is broadcast on TV by Wire Action Co., Ltd.

[0043] Television metadata can include EPG (Electronic Program Guide) program information and EPG pre-browsing counts. EPG program information is official program information from broadcasting stations. Interactive Program Guide Inc. (IPG) obtains program-related information directly from broadcasting stations across the country and manages the data in a unified manner. Specifically, it includes program name, broadcast date and time, program summary, program details, type, channel identification ID, program identification ID, etc. Furthermore, when viewing the EPG electronic program table on the homepage of a personal computer or on an application on a portable smartphone, the initial display stage is in a form in which the entire electronic program table (= schedule) can be viewed, but by selecting (clicking, etc.) an individual column of the program from here, the details of the program content can be viewed. The number of times the individual detailed page of the program has been visited before the program is broadcast is the EPG pre-browsing count.

[0044] The extraction unit 32 extracts related programs from the previous programs based on whether the target program and the previous programs are broadcasted by the same television station. For example, the extraction unit 32 extracts programs of the same television station as the target program from the previous programs as candidates for related programs. On the other hand, even if the television stations are different, the previous programs may also contain related programs (for example, professional baseball or the Tokyo Marathon, etc., sometimes cannot be associated with programs of the television stations that change on a per-program basis). Therefore, even if the target program and the previous programs are broadcasted by different television stations, the extraction unit 32 may retain the previous programs with different television stations as candidates for related programs. That is, the extraction unit 32 may only be based on whether the target program and the previous programs are broadcasted by the same television station, without discarding candidates for related programs in the previous programs (whether the target program and the previous programs are broadcasted by the same television station can also be used as an auxiliary basis).

[0045] The extraction unit 32 extracts related programs from the past programs based on whether the target program and the past programs have a predetermined common broadcast date and whether the start time, end time, and broadcast minutes of the target program and the past programs are the same or within a predetermined range.

[0046] For example, the extraction unit 32 identifies the broadcast date of the target program and previous programs as the same day of the week, or the same day of the month but different years (for example, New Year's Day or New Year's Eve every year) as specified common events, and extracts programs that have specified common events with the target program from previous programs as candidates for related programs.

[0047] For example, when the target program has the same start time, end time, and broadcast minutes as the target program, the extracting unit 32 extracts at least one of the start time, end time, and broadcast minutes as the target program from the previous programs as a candidate for the associated program. Alternatively, the extracting unit 32 uses the start time, end time, and broadcast minutes of the target program as a reference, and extracts programs within the specified range of the start time, end time, and broadcast minutes of the target program from the previous programs as candidates for the associated program. For example, when the start time is used as a reference, the previous programs that start within 2 hours before and after the start time of the target program can also be extracted as candidates for the associated program. In addition, when the end time is used as a reference, the previous programs that end within 2 hours before and after the end time of the target program can also be extracted as candidates for the associated program. In addition, when the broadcast minutes are used as a reference, the previous programs whose broadcast minutes are within the specified relative value of the broadcast minutes of the target program can also be extracted as candidates for the associated program. For example, when the target program has a broadcasting time of 60 minutes and the predetermined relative value is 0.6 to 1.6, past programs with a broadcasting time of 36 to 96 minutes may be extracted as candidates for related programs.

[0048] The extraction unit 32 extracts associated programs from past programs based on whether the amount of editing for making the program names of the target program and past programs into the same character string exceeds a specified amount of editing. The extraction unit 32 can use the "edit distance", which is an index indicating how many times the original character string needs to be edited to become the comparison target character string, to extract associated programs from past programs.

[0049] Figure 3 This is a diagram showing an example of the extraction of associated programs based on the edit distance. In Figure 3 this example, the broadcast of the program name of "○○○○○ Countdown 2019 - 2020 [Live from △△△△△!][Character]" broadcast from 23:45 on December 31, 2019 to 0:45 on January 1, 2020 is compared with the broadcast of the program name of "○○○○○ Countdown 2016 - 2017 [Once a year! □□□□□ Grand gathering!]" broadcast from 23:45 on December 31, 2016 to 0:45 on January 1, 2017. As preprocessing, while deleting the character string enclosed by brackets [], tags such as [Character] or [Broadcast] are also deleted. Through this preprocessing, the character string of "○○○○○ Countdown 2019 - 2020 [Live from △△△△△!][Character]" is converted to "○○○○○ Countdown 2019 - 2020", and the character string of "○○○○○ Countdown 2016 - 2017 [Once a year! □□□□□ Grand gathering!]" is converted to "○○○○○ Countdown 2016 - 2017". Comparing the converted character strings, three characters of the Gregorian calendar part of the former character string, "201<9> - 20<2><0>", and the Gregorian calendar part of the latter character string, "201<6> - 20<1><7>", are different. Therefore, the edit distance between the two is 3.

[0050] As an example of the rule for determining associated programs based on the edit distance, consider the following. When the preprocessed program name is less than 20 characters, the program with the edit distance within 2 and the smallest is determined as the associated program. When the preprocessed program name is 20 characters or more, for the first 20 characters of the program name, the program with the edit distance within 3 and the smallest can be determined as the associated program. Since Figure 3The "○○○○○ Countdown 2019-2020" and "○○○○○ Countdown 2016-2017" are 21 characters, so when judging according to the latter rule, for the first 20 characters of the program name, since it is a program with an edit distance of less than 3 and the smallest, it is judged that the target program and the related program are related. Of course, the rule for judging related programs based on the edit distance described here is just an example, and various design changes can be made. In addition, for example, when there is a tag [Replay] indicating replay in the program name, related programs can be searched in previous programs with the [Replay] tag. On the other hand, when there is no [Replay] tag in the program name, related programs can be searched in previous programs without the [Replay] tag.

[0051] Figure 4 This is a diagram showing an example of extracting related programs based on the broadcasting station, broadcast date, start time, end time, and program name of the target program and previous programs.

[0052] exist Figure 4 In , as the target program, a program with a broadcast station A, a broadcast date of 2019, a start time of 21:00, an end time of 22:00, and a program name of XXXXX is exemplified. Figure 4 In the figure, as candidates for related programs, there are exemplified a program whose broadcasting station is A, whose broadcasting date is △ month △ day, 2017, whose start time is 21:00, whose end time is 22:00, and whose program name is YYYYY, and a program whose broadcasting station is B, whose broadcasting date is □ month □ day, 2016, whose start time is 21:00, whose end time is 22:00, and whose program name is ZZZZZZ.

[0053] The extraction unit 32 extracts related programs from the previous programs based on the consistency or correlation between the broadcasting station, broadcast date, start time, end time, and program name of the target program and the previous programs. Since the related programs extracted by the extraction unit 32 are optimized programs for predicting the audience rating of the target program with high accuracy, the difference (prediction value 3 days ago ●●●%) and the actual value (▲▲▲%) of the audience rating of the target program can be greatly reduced (prediction-actual difference ■■■%).

[0054] The extraction unit 32 uses BERT (Bidirectional Encoder Representations from Transformers) to vectorize the program names, program summaries, and program details of the target program and previous programs, and extracts related programs from previous programs based on the cosine similarity between the vectorized target program and previous programs. That is, the text of the program name, program summary, and program details is analyzed in detail, and related programs are extracted from previous programs (vectorization of the article) based on the consistency or relevance of the words or semantic content that appear. BERT excels in natural language processing tasks such as translation, document classification, and question answering. By incorporating it into the Transformer architecture (structure), it is possible to "read the context" by learning articles from both directions (the beginning and the end of a sentence).

[0055] Figure 5 is a diagram showing a first example of BERT-based associated program extraction. Figure 5 As shown, for the target program and previous programs, the text of the program name (here ○○○○○…) is transformed into a 768-dimensional vector of the program name, the text of the program summary (here △△△△△…) is transformed into a 768-dimensional vector of the program summary, and the text of the program details (here □□□□□…) is transformed into a 768-dimensional vector of the program details.

[0056] Figure 6 is a diagram showing a second example of BERT-based related program extraction. Figure 6 In , the program name cosine similarity (here 0.99954) between the vectorized data of the text of the program name of the target program (here ○○○○○…) and the vectorized data of the program name of the previous program that is a candidate for the associated program (here ●●●●●…) is calculated. In addition, the program summary cosine similarity (here 0.97011) between the vectorized data of the program summary of the target program (here △△△△△…) and the vectorized data of the program summary of the previous program that is a candidate for the associated program (here ▲▲▲▲▲…) is calculated. In addition, the program details cosine similarity (here 0.98688) between the vectorized data of the program details of the target program (here □□□□□…) and the vectorized data of the program details of the previous program that is a candidate for the associated program (here ■■■■■…) is calculated. In addition, in Figure 6 In the example, only one past program that is a candidate for a related program is shown, but in reality, the cosine similarity of all past programs (verification programs) narrowed down by, for example, broadcasting station, start time, end time, broadcast minutes, etc. is calculated. The larger the cosine similarity, the higher the similarity with the target program, and the smaller the cosine similarity, the lower the similarity with the target program.

[0057] From the group of past programs that are candidates for related programs, programs with high cosine similarity to the target program are extracted for the program name vector, program summary vector, and program detail vector, and the ranking is calculated. On this basis, for example, related programs are extracted from the group of past programs according to the following criteria.

[0058] (1) Extract past programs that rank first in cosine similarity with the target program and have a cosine similarity of 0.99 or more as related programs. If the cosine similarities of the program name vector, program summary vector, and program detail vector are different, the cosine similarity of the program name vector is prioritized.

[0059] (2) Thresholds are set for the cosine similarity of the program name vector, program summary vector, and program detail vector, respectively. When there are two or more items whose cosine similarity does not exceed the threshold, the previous program is not extracted as an associated program. When there are two or more items whose cosine similarity exceeds the threshold, the previous program is extracted as an associated program. As an example, the threshold of the cosine similarity of the program name vector can be set to 0.97, the threshold of the cosine similarity of the program summary vector can be set to 0.98, and the threshold of the cosine similarity of the program detail vector can be set to 0.99. That is, the thresholds of the cosine similarity of the program name vector, program summary vector, and program detail vector can be made different.

[0060] (3) A past program that ranks first in the total of the cosine similarity of the program name vector, program summary vector, and program detail vector is extracted as a related program.

[0062] The prediction unit 33 predicts the ratings of the target program by using the related programs extracted by the extraction unit 32. More specifically, the prediction unit 33 predicts the ratings of the target program by applying the ratings of the related programs extracted by the extraction unit 32 to a predetermined calculation formula (algorithm). As parameters of the ratings of the related programs extracted by the extraction unit 32 used in the prediction of the ratings of the target program, for example, program broadcast period factors (program broadcast week, average of the previous 4 weeks, average of the previous 4 weeks of the next period, average of the previous 4 weeks of the previous period, average of the previous 4 weeks of the previous period, and the ratings of the previous week, etc.) can be cited. As parameters other than the ratings of the related programs extracted by the extraction unit 32 used in the prediction of the ratings of the target program, for example, program content factors (viewing experience clustering, performer information, keyword category, theme category, information type, maximum character weight, total character weight, VR program category, number of EPG pre-readings by target, number of pre-readings of subsequent programs by target, etc.) can be cited.

[0063] The calculation formula (algorithm) used by the prediction unit 33 to predict the ratings of the target program is not limited to a specific algorithm as long as it can obtain the "target output", that is, the "high-precision predicted ratings". For example, as the calculation formula (algorithm), "Random Forest" can be used. "Random Forest" is one of the methods called "group learning" that clusters the prediction results derived from a weak learning machine that learns with a simple model. It is a machine learning method with "high prediction accuracy" and "result readability". In "Random Forest", "decision trees" are used in individual weak learning machines. It can be said that this method solves the problem while making use of the advantages of "decision trees". Decision trees are prediction methods that divide space with straight lines orthogonal to the axis and assign prediction values ​​to each interval. In decision trees, since straight lines decompose space, it is widely used for analyzing simple distributed data that makes it easy to visualize the reasons for the prediction results.

[0064] The audience rating of the target program predicted by the prediction unit 33 is transmitted from the information processing device 30 to the cost calculation device 10 via the network 40. The cost calculation device 10 calculates the cost of the television commercial inserted into the target program based on the transmitted predicted audience rating of the target program (for example, multiplied by the cost per 1GRP (1%) of the rating point).

[0065] The information processing device, information processing method, and information processing program shown in the above embodiments are applied to television commercials, but are not limited thereto. The above embodiments of the present disclosure can be applied to, for example, broadcast commercials, commercials distributed over the Internet, and the like. Those skilled in the art can replace and understand the description of the above embodiments as needed. For example, in the case of being applied to broadcast commercials, the audience rating of the present disclosure can also be read as the listening rate.

[0066] The "GRP" of the present disclosure may be replaced with other indicators related to gross rating points.

[0067] In addition, the present disclosure also covers the content of replacing "ratings" with specific indicators (or the degree of improvement, deviation, etc. of specific indicators). The specific indicators can be indicators for judging the effectiveness of advertisements, intermediate indicators for improving the advertiser's key performance indicators (KPIs), etc., such as recognition rate, coverage, ROAS (Return On Advertising Spend), ROI (Return on Investment), etc. At least a part of the record of "ratings" can also be replaced by any of the above-mentioned specific indicators.

[0068] Figure 71 is a diagram showing an example of the functional configuration of the cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30. Figure 7 As shown, the cost calculation device 10, the broadcast distribution device 20 and the information processing device (audience rating prediction device) 30 include a control unit 110, a storage unit 120, a communication unit 130, an input unit 140 and an output unit 150. Figure 7 , an example of the functional blocks of the cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30 is shown, and it is also possible to have Figure 7 Other functional blocks not depicted in the figure. In addition, the structure may be configured so as not to include some functional blocks.

[0069] The control unit 110 controls the cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30. The control unit 110 can be composed of a controller, a control circuit, or a control device described based on the common knowledge of the technical field of the present invention.

[0070] The storage unit 120 stores information used in the cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30. The storage unit 120 may be composed of, for example, a memory, a storage, a storage device, etc. explained based on the common knowledge in the technical field of the present invention.

[0071] The communication unit 130 performs communication (e.g., mutual communication) between the cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30. The communication unit 130 can be composed of a transmitter / receiver, a transceiver circuit, or a transceiver device described based on the common knowledge in the technical field of the present invention. In addition, the communication unit 130 can also be composed of a transmission unit and a reception unit.

[0072] The input unit 140 receives input from the cost calculation device 10, the broadcast distribution device 20, and the information processing device (ratings prediction device) 30. In addition, the input unit 140 can also be connected to a specified device, storage medium, etc. to receive data input. The input unit 140 can, for example, output the input result to the control unit 110. The input unit 140 can be composed of input devices such as a keyboard, a mouse, and buttons, input / output terminals, and input / output circuits, etc., which are described based on the common understanding in the technical field of the present invention. In addition, the input unit 140 can also be a structure that is integrated with the display unit (for example, a touch panel).

[0073] The output unit 150 performs output of the cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30. For example, the output unit 150 may also include a display unit for displaying images, a sound output unit for outputting sounds, and the like. The display unit may be composed of a display device such as a display or a monitor described based on the common understanding in the technical field of the present invention. In addition, the sound output unit may be composed of an output device such as a speaker described based on the common understanding in the technical field of the present invention.

[0074] In addition, the block diagram used in the description of the above-mentioned embodiment represents a block of a functional unit. These functional blocks (structural parts) are implemented by any combination of hardware and / or software. In addition, the implementation method of each functional block is not particularly limited. That is, each functional block can be implemented by a physically combined device, or it can be implemented by connecting two or more physically separated devices by wire or wireless connection, and by these multiple devices.

[0075] For example, the apparatus according to the embodiment of the present disclosure (cost calculation device 10, broadcast distribution apparatus 20, and information processing apparatus (audience rating prediction apparatus) 30) may function as a computer that performs the information processing (audience rating prediction processing) of the present disclosure. Figure 8 This is a diagram showing an example of the hardware configuration of the cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30. The cost calculation device 10, the broadcast distribution device 20, and the information processing device (audience rating prediction device) 30 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0076] In addition, in the present disclosure, devices, circuits, equipment, units, servers, etc. can be replaced with each other. The hardware structure of the cost calculation device 10, the broadcast distribution device 20, and the information processing device (rating prediction device) 30 can be configured to include one or more of the devices shown in the figure, or it can be configured to exclude some of the devices.

[0077] For example, although only one processor 1001 is shown, there may be multiple processors. In addition, the processing may be performed by one processor, or the processing may be performed by two or more processors simultaneously, sequentially, or using other methods. In addition, the processor 1001 may also be implemented by one or more chips.

[0078] The functions of the cost calculation device 10, the broadcast distribution device 20, and the information processing device (rating prediction device) 30 are realized by reading the specified software (program) on the hardware such as the processor 1001 and the memory 1002, and the processor 1001 performs calculations, and controls the communication of the communication device 1004 by controlling the reading and / or writing of data in the memory 1002 and the storage 1003.

[0079] The processor 1001 controls the entire computer by, for example, running an operating system. The processor 1001 may be composed of a central processing unit (CPU) including an interface with peripheral devices, a controller, a computing device, a memory, etc. In addition, the above-mentioned control unit 110 and other units may also be implemented by the processor 1001.

[0080] In addition, the processor 1001 reads a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and performs various processes based on them. As a program, a program that causes a computer to perform at least a part of the actions described in the above embodiment is used. For example, the control unit 110 can be implemented by a control program stored in the memory 1002 and running in the processor 1001, and other functional modules can be implemented in the same way.

[0081] The memory 1002 is a computer-readable storage medium and may be composed of at least one of a read-only memory ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically EPROM), a RAM (Random Access Memory), and other suitable storage media. The memory 1002 may be referred to as a register, a cache, a main memory (main storage device), etc. The memory 1002 may store a program (program code), a software module, etc. that can be executed to implement the method according to the embodiment.

[0082] The memory 1003 may be a computer-readable storage medium, and may be composed of at least one of, for example, a floppy disk, a floppy disk (registered trademark), a magneto-optical disk (e.g., a compact disc (CD-ROM) (Compact Disc ROM), a digital versatile disc, a Blu-ray (registered trademark) disc), a removable disk, a hard disk drive, a smart card, a flash memory device (e.g., a card, a stick, a key drive), a magnetic stripe, a database, a server, and other suitable storage media. The memory 1003 may be referred to as an auxiliary storage device. In addition, the storage unit 120 described above may also be implemented by the memory 1002 and / or the memory 1003.

[0083] The communication device 1004 is hardware (transceiver) for communicating between computers via at least one of a wired network and a wireless network, and is also called a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may include a SIM card. In addition, the communication unit 130 may also be implemented by the communication device 1004.

[0084] The input device 1005 is an input device (e.g., a keyboard, a mouse, etc.) for receiving input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, etc.) for realizing output to the outside. In addition, the input device 1005 and the output device 1006 may also be an integrated structure (e.g., a touch panel). In addition, the above-mentioned input unit 140 and the output unit 150 may also be realized by the input device 1005 and the output device 1006, respectively.

[0085] In addition, the processor 1001, the memory 1002 and other devices are connected via a bus 1007 for communicating information. The bus 1007 may be composed of a single bus or different buses between devices.

[0086] In addition, the cost calculation device 10, the broadcast distribution device 20, and the information processing device (rating prediction device) 30 may include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and may also implement a part or all of each functional module through the hardware. For example, the processor 1001 may be implemented by at least one of these hardware.

[0087] (Variation Example)

[0088] Furthermore, terms explained in the present disclosure and / or terms required for understanding the present disclosure may be replaced with terms having the same or similar meanings.

[0089] The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values ​​to a specified value, or other corresponding information. In addition, the names used for parameters, etc. in this disclosure are not limited in any way.

[0090] Any of a variety of different technologies may be used to represent the information, signals, etc. described in the present disclosure. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. mentioned in the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any combination thereof.

[0091] Information, signals, etc. can also be input and output via multiple network nodes. The input and output information, signals, etc. can be stored in a specific place (such as memory), or can be managed using a table. The input / output information, signals, etc. can be overwritten, updated, or appended. The output information, signals, etc. can also be deleted. The input information, signals, etc. can also be sent to other devices.

[0092] Furthermore, notification of the prescribed information (for example, notification of "it is X") is not limited to explicit notification, but may be performed implicitly (for example, by not notifying the prescribed information or by notifying other information).

[0093] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0094] In addition, software, instructions, information, etc. may also be sent and received via at least one of a transmission medium and a signal waveform. For example, when the software is sent from a website, server or other remote source using at least one of wired technology (coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL: Digital Subscriber Line), etc.) and wireless technology (infrared, microwave, etc.), at least one of these wired technology and wireless technology is included in the definition of transmission medium.

[0095] The terms "system" and "network" used in the present invention may be used interchangeably.

[0096] The various methods / implementations described in this disclosure may be used alone, in combination, or switched as they are executed. In addition, the processing order, sequence, flow chart, etc. of the various methods / implementations described in this disclosure may be changed in order as long as there is no contradiction. For example, for the methods described in this disclosure, the elements of the various steps are presented in an exemplary order and are not limited to the specific order presented.

[0097] The description of “based on” used in the present disclosure does not mean “only based on” unless otherwise specified. In other words, “based on” means both “only based on” and “at least based on”.

[0098] Any reference to an element using the terms "first", "second", etc. used in this disclosure does not limit the quantity or order of these elements as a whole. These terms can be used as a convenient method to distinguish between two or more elements in this disclosure. Therefore, reference to a first and a second element does not mean that only two elements can be used, or that the first element must precede the second element in some form.

[0099] In this disclosure, if “include,” “including,” and variations thereof are used, these terms are meant to be as comprehensive as the term “comprising.” In addition, the term “or” used in the present invention means not an exclusive or.

[0100] In the present disclosure, for example, like a, an, and the in English, when articles are added by translation, the present disclosure may include that nouns following these articles are plural.

[0101] The invention involved in the present disclosure is described in detail above, but for those skilled in the art, the invention involved in the present disclosure is not limited to the embodiments described in the present disclosure. The invention disclosed in the present disclosure can be implemented as a modified and altered mode without departing from the subject matter and scope of the invention determined according to the records of the claims. Therefore, the description of the present disclosure is intended for illustrative purposes and does not provide any restrictive meaning for the invention according to the present disclosure.

[0102] This application is based on Japanese patent application No. 2022-112231 filed on July 13, 2022, the entire contents of which are expressly incorporated herein by reference.

Claims

1. An information processing device, characterized in that: have: an acquisition unit that acquires past programs that are candidates for related programs used for audience rating prediction of the target program; and An extracting unit extracts the related program from the past program based on the broadcasting station, broadcast date and time, program name, and program content of the past program.

2. The information processing device according to claim 1, characterized in that The program further includes a prediction unit that predicts the audience rating of the target program by using the related program.

3. The information processing device according to claim 1 or 2, characterized in that: The extraction unit extracts the related program from the previous program based on whether the target program and the previous program are broadcasted by the same television station.

4. The information processing device according to claim 1 or 2, characterized in that: The extraction unit extracts the related program from the past programs based on whether there are specified common items in the broadcast dates of the target program and the past programs and whether the start time, end time, and broadcast minutes of the target program and the past programs are the same or within a specified range.

5. The information processing device according to claim 1 or 2, characterized in that: The extraction unit extracts the related program from the past program based on whether the amount of editing for making the program names of the target program and the past program have the same character string exceeds a predetermined amount of editing.

6. The information processing device according to claim 1 or 2, characterized in that: The extraction unit vectorizes the program names, program summaries, and program details of the target program and the previous programs by using BERT (Bidirectional Encoder Representations from Transformers), and extracts the related programs from the previous programs based on the cosine similarity between the vectorized target program and the previous programs.

7. An information processing method, characterized in that: have: A step of acquiring past programs that are candidates for related programs used for audience rating prediction of a target program; and A step of extracting the related program from the past programs based on the broadcasting station, broadcast date and time, program name, and program content of the past programs.

8. An information processing program, characterized in that Causes the computer to execute: A step of acquiring past programs that are candidates for related programs used for audience rating prediction of a target program; and A step of extracting the related program from the past programs based on the broadcasting station, broadcast date and time, program name, and program content of the past programs.

Images