A judgment is often made based on past experience and knowledge.

So what is a machine made of?

For ordinary computer algorithms, the algorithm makes a judgment through the programming language.

Here is a simple example of if, else statements (for the sake of simplicity, the judgment conditions and output are not strictly programmed, do not use a bar).

if (reader x voted for recommendation):

Reader X is very handsome

else：

Reader X looks average

For ordinary computer algorithms, through the above judgment statements, it knows that the readers who voted for the recommendation are handsome.

But if the programmer finds out one day that some readers who voted for recommendation also seem to look quite average, so he optimizes the algorithm and changes the judgment condition to (reader x voted for recommendation and reader x voted for a month).

At this time, for the algorithm, only readers who have voted for both the recommendation vote and the monthly pass are handsome.

Later, the programmer will find that no matter how much he puts his judgment on it, it seems that one or two readers will jump out and overturn his conclusions, and it will be very difficult for him to manually make rules for the computer to accurately identify handsome readers.

This is where machine learning algorithms come in.

So how do machine learning algorithms do it?

We only need to randomly select a certain number of readers (called training data in the field of machine learning) to make a table, in which some attributes of these readers are recorded, such as whether they have voted for recommendations, whether they have voted for monthly tickets, whether they have left comments, whether they have liked, whether they have been rewarded, etc. (called features in the field of machine learning), and record the conclusion in the last column, that is, whether they are handsome or not (called labels in the field of machine learning).

This training data is fed to a machine learning algorithm, and at the end of the training, it learns a model about the relationship between the reader's characteristics and whether the reader is handsome.

At this time, let it judge whether a new reader is handsome, and he will give a probability that the reader is handsome and not handsome according to this training model.

Obviously, the larger the amount of training data given to machine learning, the higher the probability that it will come to the correct conclusion after learning.

That's why machine learning is widely used in many work scenarios, such as when a road camera takes a picture and directly identifies whether the driver is driving, smoking, talking on the phone, holding the steering wheel with one hand, chatting with passengers, or doing something else.

With such a powerful learning ability, combined with equally advanced artificial intelligence technology, it is not surprising that people are worried about the so-called intellectual crisis.

However, there is a big difference between the machine learning mentioned in this paper and the machine learning that Gu Feng learned based on his previous life cognition.

Based on the world's more advanced artificial intelligence technology and digital life technology, machine learning can directly teach language and behavior.

This is the same as parents teaching their children what a pig is and how to write.

In fact, in essence, this process returns to the most primitive algorithm, that is, the programmer makes the computer do something through the algorithm.

It's just that in this kind of machine learning in the field of digital life, the digital life can automatically recognize the words it hears and the phenomena it sees, and then generate a new code on its own, and this new code is its cognition of a passage or a certain phenomenon.

Although the first digital life has not yet been born, people are far more assured that the artificial intelligence born under this technology is far more reassuring than the artificial intelligence of the previous life.

After all, under the limitations of digital life, this form of artificial intelligence cannot learn quickly by freely shuttling through the Internet, and it must also be like people, it needs to listen, watch, and do in order to gradually learn and progress, and improve its cognition and ability.

Gu Feng did not hesitate in his heart and gave a big thumbs up to the scientists.

This kind of technology, not in the field of games, is simply a tyrannical thing.

In his previous life, more than ten years before he traveled through, there were already many games that played APC gimmicks to attract players, that is, NPCs that claimed to have AI.

In fact, this is understandable, after all, although players don't particularly care, but if the NPCs in the game can be more humane and flesh-and-blood, who wants to face a person who will always only say a few words?

According to the information that Gu Feng consulted, digital life technology may be able to mature to the point where it can be commercialized in just two years.

Now that the technical bottleneck has been confirmed to be not a problem, the super IP plan in Gu Feng's heart can finally start planning and strive to be implemented as soon as possible.

Opening a blank document, Gu Feng lightly knocked down the title on the first line - Pokémon World.

Gu Feng's speed of writing the plan this time is far less fast than when he wrote the game design book before, at this time, he is like a bitter and hateful online article Xiaoba, when he thinks about it, he has a stomach full of thoughts, and when he really writes, he often ponders for a long time before he can hold back a short paragraph.

Gu Feng didn't know too well whether the Pokémon in the previous life was the animation or the game, but it didn't matter, since he wanted to maximize the value of the IP, the game definitely couldn't be done before the animation.

Manga games and game manga are completely different things.

In addition to animation and games, Gu Feng also considered and movies in his plan.

Of course, the movie here does not refer to the animated theatrical version, but a movie like "Pokémon: Detective Pikachu", after all, the audience of the animated theatrical version is still the group of people who watch the animation, and the second creation movie like "Pokémon: Detective Pikachu" can attract more people who don't like to watch animation.

However, the planning of the film is not particularly necessary, and the priority in the planning should not be too high.

As for animation, Gu Feng also has a bold idea, he doesn't plan to use the original animation.

The reason is very simple, although the original is a classic, but after all, it is still a little younger, and sometimes he even wonders that if the Pokémon animation was born twenty years later, will it still be popular? Probably not.

As far as the theme of Pokémon is concerned, it can be more mature in story arrangement and character building, after all, the ultimate goal is the game, although theoretically although the expected VR Pokémon is for all ages regardless of gender, but in fact, Gu Feng knows that the real core player group must be young players in their 18 to 20s.

Competitiveness, energy, and enthusiasm for game research are all characteristics of players of this age, and since Gu Feng wants to make it an epoch-making competitive masterpiece, capturing the hearts of this group of players is naturally the top priority.

Therefore, it became an imperative choice to abandon the original work and make the animation more mature.