A company, and the products or services sold by the company, may be referred to generally as a brand. The company/brand may use a creative agency which provides content for the brand's advertising campaign. The content may include text, images, and/or sounds.
The company may initially specify some general subjective goals for the campaign. For example, the campaign may have an overall objective and a general theme. The company also may want the campaign directed to a specific audience, such as millennials. The company may inform the creative agency of these general subjective goals.
The creative agency generates content based on these campaign goals. The company and creative agency then go through multiple iterations of modifying the content to conform with the campaign goals. During the review process, the company also may specify other campaign requirements and goals not previously communicated to the creative agency. This iterative process of reviewing and editing content is time consuming and expensive.
A content compliance system uses Artificial Intelligence (AI) to generate objective verification which checks if content complies with brand campaign criteria. The content compliance system may force the company to select specific brand criteria listed on a user interface. The selected brand criteria are then readily displayed to the creative agency.
The content compliance system then compares the selected brand criteria with content generated by the creative agency. The content compliance system uses AI algorithms to generate a compliance score that provides a real-time objective indication of the compliance of the creative content with the selected brand criteria. The creative agency can then modify the creative content and receive a real-time updated compliance score.
This machine learning based compliance system provides real-time objective feedback regarding brand criteria compliance that reduces the overall development time for what was previously thought to be a subjective content review process. Thus, brand campaigns can be launched in less time and less expensively.
Content compliance engine 104 displays a list of brand directives 108 on user interface 122. For example, content compliance engine 104 may display a set of possible objectives 108A for the campaign, a set of possible audiences 108B for the campaign, a set of possible themes 108C for the campaign, and a content format 108D for the campaign. This is just an example set of brand directives 108 and additional brand directives are discussed in more detail below.
Compliance engine 104 may force the company/brand to select some combination of brand directives 108. This provides the advantage of forcing the company to clearly specify objective identifiable items for including in the campaign content. Content compliance engine 104 may store the selected brand directives 108 in a database 110.
The creative agency may access content compliance system 100. Compliance engine 104 may display a list of the previously selected brand directives 108 on user interface 122. The creative agency creates content 124 that tries to comply with selected brand directives 108. For example, the creative agency may create text 124A that communicates the selected objectives 108A and themes 108C in a manner that engages the selected audience 108B and uses the selected content format 108D. Content 124 may also include pictures, videos, images, etc. 124B and/or a company logo 124C that comply with content format 108D and any other selected brand directives 108.
Compliance engine 104 parses content 124 and compares the parsed content with selected brand directives 108. In one example, compliance engine 104 uses machine learning algorithms 106 and any other known natural language processing to identify different messages, phrases, subjects, images, tones, attributes, brands, sentiment, or any other content that may be associated with any of selected brand directives 108. Other known software programs can identify formatting used in content 124, such as different types, sizes, colors positions, actions, etc. of objects in content 124. Example software programs are described at https://arxiv.org/abs/1512.00567 and https://pjreddie.com/media/files/papers/YOLOv3.pdf which are incorporated by reference in their entireties and used for training task specific models.
Content compliance system 100 also may store a set of suggested phrases 112 for different types of brand directives 108. Suggested phrases 112 may have been used and tested in previous campaigns and determined to generate high engagement with different audiences and/or determined to be effective in achieving other brand directives 108. For example, a certain phrase “With research we have found” may have been determined through benchmarking to produce high engagement with millennials. Content compliance system 100 may store “With research we have found” as one of suggested phrases 112 associated with a millennials category in audience 108B.
In one example, compliance engine 104 may use suggested phrases 112 to determine compliance of content 124 with brand directives 108. For example, brand directives 108 may include millennials in audience 108B. Compliance engine 104 may use natural language processing to determine if any phrases in content 124 are similar to the suggested phrases 112 associated with millennials.
Content compliance engine 104 generates compliance results 126 based on the comparison of content 124 with selected brand directives 108. For example, as part of compliance results 126, compliance engine 104 may count and display a compliance score 126A that identifies the number of selected brand directives 108 contained in content 124.
Compliance results 126 also may include a resonance level 126B that indicates a high, medium, or low level of resonance of content 124 with the selected audience. Compliance engine 104 may generate resonance level 126B based on the similarity of phrases in content 124 with suggested phrases 112 associated with the selected audience. Other factors taken into account when determining the resonance level 126B may include objectives 108A, themes 108C, content format 108D, images 124B or any other brand directives 108 in content 124 that has been determined to generate user engagement.
As part of compliance results 126, compliance engine 104 may display individual compliance indicators 126C and 126D showing if particular brand directives 108 exist in content 124. For example, compliance indicator 126C shows that content 124 contains the objectives 108A selected in brand directives 108 and compliance indicator 126D shows that content 124 does not comply with audience 108B selected in brand directives 108.
As mentioned above, compliance results 126 can be generated by compliance engine 104 in real-time as soon as content 124 is generated. The creative agency can then use compliance results 126 to modify content 124 in real-time to increase compliance score 126A and resonance score 126B. The creative agency can also view individual compliance indicators 126C and 126D to determine what specific brand directives 108 are not currently included in content 124.
The creative agency may repeatedly modify and resubmit content 124 to compliance system 100 until compliance results 126 reach an acceptable compliance score 126A and resonance level 126B. In one example, compliance engine 104 may be programmed with compliance threshold scores, such as 90% compliance with all brand directives 108 and a high resonance level with viewers. Compliance engine 104 may automatically display a message on user interface 122 when content 124 reaches the acceptable compliance thresholds.
After reaching the acceptable compliance thresholds, the creative agency may submit content 124 to the brand for final approval or may publish content 124 on any identified media channels, such as posting content 124 on one or more social media websites. Thus, content compliance system 100 provides substantial time savings by reducing the number of iterations needed to produce content 124 that complies with brand directives 108.
In operation 152, content compliance system 100 receives content 124 created by the creative agency. Compliance system 100 may display a summary of the selected brand directives 108 to the creative agency via the user interface. The creative agency then produces content 124 based on the displayed brand directives 108.
In operation 154, compliance system 100 compares content 124 produced by the creative agency with brand directives 108 selected by the company/brand. As explained above, known machine learning algorithms are used to determine if content 124 contains selected brand directives 108.
In operation 156, compliance system 100 outputs compliance results 126 based on comparisons 154 of content 124 with brand directives 108. As mentioned above, compliance system 100 may generate a compliance score 126A identifying the number of selected compliance directives 108 contained in the content 124, generate a resonance level 126B indicating how well content 124 will resonate with the viewing audience, and display compliance indicators 126C and 126D identifying which specific compliance directives 108 are contained in content 124.
In operation 158, compliance system 100 determines if content 124 is complaint with the brand directives. For example, compliance system 100 may determine if compliance score 126A and resonance level 126B is above particular threshold levels. If compliance results 126 are above the threshold numbers or percentages, compliance system 100 may publish the content in operation 160. For example, compliance system 100 may post content 124 on a social media network selected by the company/brand as one of brand directives 108. Alternatively, compliance system 100 may send content 124 to the company/brand for a final review prior to publishing in operation 160.
If not compliant with the brand directives 108 in operation 158, compliance system 100 may send content 124 back to the creative agency and/or notify the creative agency that content 124 requires further editing. The creative agency then edits content 124 in operation 152 and resubmits the edited content to compliance system 100 for another comparison with brand directives 108 in operation 154. This iterative automated review process repeats until content 124 meets a specified compliance level in operation 158.
Some example deep learning algorithms that perform message and phrase level classification are described in U.S. patent application Ser. No. 16/251,934; entitled: CONTENT INSIGHT SYSTEM; filed Jan. 18, 2019, which is herein incorporated by reference. Subjects 152A and attributes 152B identified in content in the above referenced application may be compared with selected brand directives 108. Compliance system 100 may identify any brand directives 108 matching any of the identified subjects 152A and attributes 152B in content 124.
Other example deep learning algorithms and sequence labeling algorithms for message and phrase level classification of content are described at https://en.wikipedia.org/wiki/Named-entity_recognition and at https://en.wikipedia.org/wiki/Dependency_grammar which are herein incorporated by reference in their entirety.
Deep learning algorithms may refer any machine learning algorithm with multiple non-linear layers that can learn feature hierarchies. Another example deep learning algorithm is word2vec that may generate multi-dimensional word vectors from content 124 and brand directives 108. Content vectors in the same multi-dimensional space location as brand directive vectors may indicate the brand directive 108 is contained in content 124.
As mentioned above, brand directive 108A may include different selectable objectives/goals 186. Example selectable objectives/goals 186 may include: provide information and support, generate brand awareness, establish though leadership, inspire trust and loyalty, develop community, demand generation, increase sales.
Brand directive 108B may include different selectable audiences 188 that include: generation Z, millennials, generation X, boomers, silent generation, economic buyer, champion, technical buyer, and practitioner. Generation Z may be between ages 15-20, millennials may be between ages 21-34, generation X may be between ages 35-49, boomers may be between ages 50-64, and silent generation may be over age 65. The economic buyer may evaluate a return on investment (ROI), a champion may be looking for implementation of a solution, a technical buyer may evaluate feasibility, and the practitioner may evaluate a user experience. Of course, all of these are just examples of any audience 188 where a brand may want to direct content.
A brand directive 108F may identify different selectable channels 192 for publishing content 124 including social media platforms such as: Facebook®, Twitter®, Instagram®, LinkedIn®, YouTube®, etc.
A brand directive 108C, as mentioned above in
A selectable low conscientiousness 210B may be associated with efficient/organized and a selectable high conscientiousness 210B may be associated with easy-going/careless. A selectable low extraversion 210C may be associated with outgoing/energetic and a selectable high extraversion 210C may be associated with solitary/reserved. A selectable low agreeable 210D may be associated with friendly/compassionate and a selectable high agreeable 210D may be associated with challenging/detached. A selectable low emotional range 210E may be associated with sensitive/nervous and a selectable high emotional range 210E may be associated with secure/confident. More information about this can be found at https://en.wikipedia.org/wiki/Big_Five_personality_traits which is incorporated in its entirety.
Compliance system 100 may display a check mark or some other indicator when the selected brand directive 108 is identified in content 124. For example, user interface 122 shows that compliance system 100 detected identified thought leadership goal 186 in content 124. Compliance system 100 also determined content 124 was adequately directed to selected millennial audience 188 but was not adequately directed to generation X audience 188.
Compliance system 100 determined content 124 did not contain data needed for posting on selected LinkedIn® and Twitter® channels 192. Compliance results 126 also show that content 124 does not include selected long-form text, short-form video, and animated GIFs 196. Compliance results 126 may identify any other selected brand directive 108, such as tones 198, customer journey stages 190, and themes 194.
Compliance system 100 also may display suggestive phrases 112 for the different selected brand directives 108. As explained above, different phrases may be associated with different brand directives 108. For example, based on prior benchmarking, it may be discovered that particular phrases 112 may increase engagement with particular audiences or with all audiences.
Compliance system 100 may display suggestive phrases 112 with the associated brand directives 108. For example, compliance system 100 may determine current content 124 will not highly engage the generation X audience. Prior benchmarking may have determined suggestive phrases 112 in
The content compliance engine 104 and scheme used for identifying compliance of content with selected campaign directives provides a substantial improvement in computer technology and operation by more efficiently processing and storing content in a database system in real time to then more quickly determine if and where specific data items are located in electronic documents.
While only a single computing device 1000 is shown, the computing device 1000 may include any collection of devices or circuitry that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the operations discussed above. Computing device 1000 may be part of an integrated control system or system manager, or may be provided as a portable electronic device configured to interface with a networked system either locally or remotely via wireless transmission.
Processors 1004 may comprise a central processing unit (CPU), a graphics processing unit (GPU), programmable logic devices, dedicated processor systems, micro controllers, or microprocessors that may perform some or all of the operations described above. Processors 1004 may also include, but may not be limited to, an analog processor, a digital processor, a microprocessor, multi-core processor, processor array, network processor, etc.
Some of the operations described above may be implemented in software and other operations may be implemented in hardware. One or more of the operations, processes, or methods described herein may be performed by an apparatus, device, or system similar to those as described herein and with reference to the illustrated figures.
Processors 1004 may execute instructions or “code” 1006 stored in any one of memories 1008, 1010, or 1020. The memories may store data as well. Instructions 1006 and data can also be transmitted or received over a network 1014 via a network interface device 1012 utilizing any one of a number of well-known transfer protocols.
Memories 1008, 1010, and 1020 may be integrated together with processing device 1000, for example RAM or FLASH memory disposed within an integrated circuit microprocessor or the like. In other examples, the memory may comprise an independent device, such as an external disk drive, storage array, or any other storage devices used in database systems. The memory and processing devices may be operatively coupled together, or in communication with each other, for example by an I/O port, network connection, etc. such that the processing device may read a file stored on the memory.
Some memory may be “read only” by design (ROM) by virtue of permission settings, or not. Other examples of memory may include, but may be not limited to, WORM, EPROM, EEPROM, FLASH, etc. which may be implemented in solid state semiconductor devices. Other memories may comprise moving parts, such a conventional rotating disk drive. All such memories may be “machine-readable” in that they may be readable by a processing device.
“Computer-readable storage medium” (or alternatively, “machine-readable storage medium”) may include all of the foregoing types of memory, as well as new technologies that may arise in the future, as long as they may be capable of storing digital information in the nature of a computer program or other data, at least temporarily, in such a manner that the stored information may be “read” by an appropriate processing device. The term “computer-readable” may not be limited to the historical usage of “computer” to imply a complete mainframe, mini-computer, desktop, wireless device, or even a laptop computer. Rather, “computer-readable” may comprise storage medium that may be readable by a processor, processing device, or any computing system. Such media may be any available media that may be locally and/or remotely accessible by a computer or processor, and may include volatile and non-volatile media, and removable and non-removable media.
Computing device 1000 can further include a video display 1016, such as a liquid crystal display (LCD) or a cathode ray tube (CRT) and a user interface 1018, such as a keyboard, mouse, touch screen, etc. All of the components of computing device 1000 may be connected together via a bus 1002 and/or network.
For the sake of convenience, operations may be described as various interconnected or coupled functional blocks or diagrams. However, there may be cases where these functional blocks or diagrams may be equivalently aggregated into a single logic device, program or operation with unclear boundaries.
Having described and illustrated the principles of a preferred embodiment, it should be apparent that the embodiments may be modified in arrangement and detail without departing from such principles. Claim is made to all modifications and variation coming within the spirit and scope of the same corresponding time period.