#include <atcoder/all>
using namespace atcoder;
#include <bits/stdc++.h>
using namespace std;
// #include <boost/multiprecision/cpp_int.hpp>
#pragma GCC target("avx2")
#pragma GCC optimize("O3")
#pragma GCC optimize("unroll-loops")
#define rep(i, n) for (int i = 0; i < (int)(n); i++)
#define rep2(i,a,b) for (int i = (int)(a); i < (int)(b); i++)
#define all(v) v.begin(),v.end()
#define inc(x,l,r) ((l)<=(x)&&(x)<(r)) 
#define Unique(x) sort(all(x)), x.erase(unique(all(x)), x.end())
#define pcnt __builtin_popcountll
typedef long long ll;
#define int ll
using ld = long double;
using vi = vector<int>;
using vs = vector<string>;
using P = pair<int,int>;
using vp = vector<P>;
// using Bint = boost::multiprecision::cpp_int;
template<typename T1,typename T2> bool chmax(T1 &a, const T2 b) {if (a < b) {a = b; return true;} else return false; }
template<typename T1,typename T2> bool chmin(T1 &a, const T2 b) {if (a > b) {a = b; return true;} else return false; }
template<typename T> using priority_queue_greater = priority_queue<T, vector<T>, greater<T>>;
template<typename T1,typename T2> ostream &operator<< (ostream &os, const pair<T1,T2> &p){os << p.first <<" "<<p.second;return os;}
ostream &operator<< (ostream &os, const modint1000000007 &m){os << m.val();return os;}
istream &operator>> (istream &is, modint1000000007 &m){ll in;is>>in;m=in;return is;}
ostream &operator<< (ostream &os, const modint998244353 &m){os << m.val();return os;}
istream &operator>> (istream &is, modint998244353 &m){ll in;is>>in;m=in;return is;}
template<typename T> istream &operator>>(istream& is,vector<T> &v){for(T &in:v)is>>in;return is;}
template<class... T> void input(T&... a){(cin>> ... >> a);}
#ifdef LOCAL
template<typename T> ostream &operator<<(ostream &os,const vector<T> &v){os<<"\x1b[32m";rep(i,v.size())os<<v[i]<<(i+1!=v.size()?" ":"");os<<"\x1b[0m";return os;}
template<class T> int print(T& a){cout << "\x1b[32m"<< a<< '\n' << "\x1b[0m";return 0;}
template<class T,class... Ts> int print(const T&a, const Ts&... b){cout << "\x1b[32m" << a;(cout<<...<<(cout<<' ',b));cout<<'\n' << "\x1b[0m";return 0;}
#else
template<typename T> ostream &operator<<(ostream &os,const vector<T> &v){rep(i,v.size())os<<v[i]<<(i+1!=v.size()?" ":"");return os;}
template<class T> int print(T& a){cout << a<< '\n';return 0;}
template<class T,class... Ts> int print(const T&a, const Ts&... b){cout << a;(cout<<...<<(cout<<' ',b));cout<<'\n';return 0;}
#endif
#define VI(v,n) vi v(n); input(v)
#define INT(...) int __VA_ARGS__; input(__VA_ARGS__)
#define STR(...) string __VA_ARGS__; input(__VA_ARGS__)
#define CHAR(...) char __VA_ARGS__; input(__VA_ARGS__)
int sign(ll x){return x>0?1:x<0?-1:0;}
ll ceil(ll x,ll y){assert(y!=0);if(sign(x)==sign(y))return (x+y-1)/y;return -((-x/y));}
ll floor(ll x,ll y){assert(y!=0);if(sign(x)==sign(y))return x/y;if(y<0)x*=-1,y*=-1;return x/y-(x%y<0);}
ll abs(ll x,ll y){return abs(x-y);}
ll bit(int n){return 1ll<<n;}
bool ins(string s,string t){return s.find(t)!=string::npos;}
P operator+ (const P &p, const P &q){ return P{p.first+q.first,p.second+q.second};}
P operator- (const P &p, const P &q){ return P{p.first-q.first,p.second-q.second};}
int yesno(bool ok,string y="Yes",string n="No"){ cout<<(ok?y:n)<<endl;return 0;}
int YESNO(bool ok,string y="YES",string n="NO"){ cout<<(ok?y:n)<<endl;return 0;}
int di[]={-1,0,1,0,-1,-1,1,1};
int dj[]={0,1,0,-1,-1,1,-1,1};
const ll INF = 8e18;
//using mint = modint1000000007;
using mint = modint998244353;
//mint stom(const string &s,int b=10){mint res = 0;for(auto c:s)res *= b,res += c-'0';return res;}
class comb{
private:
    int MAX_N;
    vector<mint> _fac,_ifac,_inv;
    void init(){
        for(int i=2;i<=MAX_N;i++)_fac[i]=_fac[i-1]*i;
        _ifac[MAX_N]=1/_fac[MAX_N];
        for(int i=MAX_N-1;i>=1;i--)_ifac[i]=_ifac[i+1]*(i+1);
        for(int i=2;i<MAX_N;i++)_inv[i] = _fac[i-1]*_ifac[i];
    }
public:
    comb(int n=20002000):MAX_N(n),_fac(n+1,1),_ifac(n+1,1),_inv(n+1,1){init();}
    mint fac(int k){assert(k<=MAX_N);return _fac[k];}
    mint ifac(int k){assert(k<=MAX_N);return _ifac[k];}
    mint inv(int k){assert(k<=MAX_N);return _inv[k];}
    mint nPr(int n,int r){if(r<0||n<r)return 0;return fac(n)*ifac(n-r);}
    mint nCr(int n,int r){if(r<0||n<r)return 0;if(n>MAX_N||r>MAX_N)return nCr_naive(n,r);return nPr(n,r)*ifac(r);}
    mint nHr(int n,int r,int low=0){r-=n*low;if(n==0&&r==0)return 1;if(n<=0||r<0)return 0;return nCr(n+r-1,r);}
    mint nCr_naive(int n,int r){
        chmin(r,n-r);
        mint res = 1;
        rep(i,r)res*=(n-i),res*=_inv[r-i];
        return res;
    }
} com;
signed main() {
    cin.tie(0);
    ios_base::sync_with_stdio(false);
    cout << fixed << setprecision(20);

    INT(n,p);
    if(p>n)return print(com.fac(n)-1);
    vector<mint> dp(n+1);//dp[i]:=長さpのサイクルをi個作るとき
    dp[0] = 1;
    rep(i,n)if((i+1)*p<=n){
        dp[i+1] = dp[i]*com.inv(i+1)*com.nCr(n-p*i,p)*com.fac(p)*com.inv(p);
    }
    print(com.fac(n)-accumulate(all(dp),mint(0)));
    return 0;
}