The Next Communication Paradigm Led by AI-Based Semantic Communication

Shannon's Law

Contemporary communication has evolved based on Shannon's Law. This is a theory that determines the limits of network communication, and the attempts made were aimed at increasing the maximum channel capacity of the formula described below. Examples include technologies such as MIMO (Multiple Input Multiple Output). These technologies represent efforts to achieve higher channel capacity based on Shannon's theory.

Shannon's Law is expressed by the following formula for calculating channel capacity: $$C = B \cdot \log_{2}(1 + \frac{S}{N})$$ author: yoonhyunwoo

These respectively signify Channel Capacity ( $C$ To put it simply in words, the **Maximum Communication Speed ( $C$

Once this law for calculating channel capacity emerged, the communication industry began to concentrate efforts on increasing channel capacity. Consequently, for approximately 70 years, most innovations in communication have been achieved through the improvement of channel capacity.

However, in the current era, processing resources have advanced significantly. Communication has progressed from the era of sending text to the point of sending spatial vectors. A limitation has begun to emerge in reliably segmenting and transmitting all this data. For instance, the data generated by an autonomous vehicle can amount to several terabytes per day, and it is nearly impossible for the current communication network to handle this. Simply laying more cables and installing more antennas reaches an economic and physical limit for resolution.

Thus, a paradigm began to be researched that moves away from the existing paradigm of transmitting every bit accurately and instead seeks to transmit only the context by introducing intelligence into communication. (The concept itself has existed for decades.) And this is a change resulting from the powerful advancement of recent intelligent models and the increased necessity for the communication of even larger data volumes.

This is referred to as Semantic Communication, as it is communication that exchanges meaning (意味).

Semantic communication

While conventional communication transmitted the entirety of the data, semantic communication now aims to transmit only the core meaning contained within it, namely the context.

This problem was already raised in the communication model of Shannon and Weaver, who divided the maturity of communication into three levels:

1. Technical Problem: How accurately can a symbol be transmitted? (This is the core domain of my theory.)
2. Semantic Problem: How accurately does the transmitted symbol convey the intended 'meaning'?
3. Effectiveness Problem: How effectively does the conveyed meaning influence the receiver's behavior?

The advancement of communication has largely resolved the technical problem, and the current task involves translating the semantic and effectiveness problems.

The difference between maturity level 1 and levels 2 and 3 (Semantic communication) is typically illustrated using the example of a burning house.

A house is on fire.

In the current communication paradigm, this scene is meticulously digitized and transmitted as a photograph.

In semantic communication, instead of sending all the data, such as "black smoke is coming from the window and flames are visible," the method conveys only the core 'meaning,' such as "Fire outbreak, immediate dispatch required." This approach boldly omits unnecessary information and aims for the recipient to take a specific action (dispatch).

If the end-to-end communication involves parties possessing the same knowledge base within the category of firefighting, this can dramatically reduce the volume of transmission data required for situational awareness.

The core encoding/decoding logic of such semantic communication operates on the application layer, despite being a communication paradigm. On the transmitting side, the semantic encoder converts the given data into semantic data, and on the receiving side, the semantic decoder processes it into a form usable by the back-end source. Both will take the form of an inference model or similar with the same knowledge base, which enables communication to exchange semantics without the need for massive data transmission.

Naturally, this is guaranteed based on the completeness of the existing communication paradigm. First, it must be technically possible to transmit symbols accurately, and this level of maturity has already been achieved. The main challenge now is how well the transmitted symbols convey and interpret the semantics of the information, and research into this is just beginning.

However, unlike the existing syntactic communication system, a communication system based on such semantic context is highly likely to encounter problems because it relies on AI, etc., for reliability. Even if the parties possess an identical Knowledge Base, different interpretations may emerge from the black-box region of the model.

Postscript

It is suggested that in 6G (6th generation) mobile communication, this semantic communication will be applied, leading to an intelligent internet system, but there is a question mark regarding why a paradigm operating on the application layer becomes a research task for mobile communication companies. My intuition suggests that mobile communication companies play the role of ensuring maturity level 1, where symbols and bits are transmitted accurately technically, and the point at which semantic communication operates is already within the domain of application programs.

Furthermore, there is a question as to whether this constitutes a new paradigm in communication technology, which must fundamentally uphold reliability. I also harbor such doubts and personally hold a somewhat negative stance.

Nevertheless, the reason for writing this article is that the next paradigm of mobile communication is unfolding in a quite interesting manner. The introduction of satellite internet for the expansion of channel capacity is virtually a fait accompli with the emergence of Project Kuiper, Starlink, etc., and the attempt to overcome the limitations constrained by Shannon's Law in a new form was quite fascinating.