#include <algorithm>
#include <bitset>
#include <cassert>
#include <chrono>
#include <cmath>
#include <cstdlib>
#include <cstring>
#include <deque>
#include <functional>
#include <iomanip>
#include <iostream>
#include <map>
#include <queue>
#include <random>
#include <set>
#include <stack>
#include <string>
#include <unordered_map>
#include <unordered_set>
#include <vector>

using namespace std;
typedef long long ll;

template <typename T> T inverse(T a, T m) {
  T u = 0, v = 1;
  while (a != 0) {
    T t = m / a;
    m -= t * a;
    swap(a, m);
    u -= t * v;
    swap(u, v);
  }
  assert(m == 1);
  return u;
}

template <typename T> class Modular {
public:
  using Type = typename decay<decltype(T::value)>::type;

  constexpr Modular() : value() {}
  template <typename U> Modular(const U &x) { value = normalize(x); }

  template <typename U> static Type normalize(const U &x) {
    Type v;
    if (-mod() <= x && x < mod())
      v = static_cast<Type>(x);
    else
      v = static_cast<Type>(x % mod());
    if (v < 0)
      v += mod();
    return v;
  }

  const Type &operator()() const { return value; }
  template <typename U> explicit operator U() const {
    return static_cast<U>(value);
  }
  constexpr static Type mod() { return T::value; }

  Modular &operator+=(const Modular &other) {
    if ((value += other.value) >= mod())
      value -= mod();
    return *this;
  }
  Modular &operator-=(const Modular &other) {
    if ((value -= other.value) < 0)
      value += mod();
    return *this;
  }
  template <typename U> Modular &operator+=(const U &other) {
    return *this += Modular(other);
  }
  template <typename U> Modular &operator-=(const U &other) {
    return *this -= Modular(other);
  }
  Modular &operator++() { return *this += 1; }
  Modular &operator--() { return *this -= 1; }
  Modular operator++(int) {
    Modular result(*this);
    *this += 1;
    return result;
  }
  Modular operator--(int) {
    Modular result(*this);
    *this -= 1;
    return result;
  }
  Modular operator-() const { return Modular(-value); }

  template <typename U = T>
  typename enable_if<is_same<typename Modular<U>::Type, int>::value,
                     Modular>::type &
  operator*=(const Modular &rhs) {
#ifdef _WIN32
    uint64_t x = static_cast<int64_t>(value) * static_cast<int64_t>(rhs.value);
    uint32_t xh = static_cast<uint32_t>(x >> 32), xl = static_cast<uint32_t>(x),
             d, m;
    asm("divl %4; \n\t" : "=a"(d), "=d"(m) : "d"(xh), "a"(xl), "r"(mod()));
    value = m;
#else
    value = normalize(static_cast<int64_t>(value) *
                      static_cast<int64_t>(rhs.value));
#endif
    return *this;
  }
  template <typename U = T>
  typename enable_if<is_same<typename Modular<U>::Type, int64_t>::value,
                     Modular>::type &
  operator*=(const Modular &rhs) {
    int64_t q = static_cast<int64_t>(static_cast<long double>(value) *
                                     rhs.value / mod());
    value = normalize(value * rhs.value - q * mod());
    return *this;
  }
  template <typename U = T>
  typename enable_if<!is_integral<typename Modular<U>::Type>::value,
                     Modular>::type &
  operator*=(const Modular &rhs) {
    value = normalize(value * rhs.value);
    return *this;
  }

  Modular &operator/=(const Modular &other) {
    return *this *= Modular(inverse(other.value, mod()));
  }

  template <typename U>
  friend bool operator==(const Modular<U> &lhs, const Modular<U> &rhs);

  template <typename U>
  friend bool operator<(const Modular<U> &lhs, const Modular<U> &rhs);

  template <typename U>
  friend std::istream &operator>>(std::istream &stream, Modular<U> &number);

private:
  Type value;
};

template <typename T>
bool operator==(const Modular<T> &lhs, const Modular<T> &rhs) {
  return lhs.value == rhs.value;
}
template <typename T, typename U>
bool operator==(const Modular<T> &lhs, U rhs) {
  return lhs == Modular<T>(rhs);
}
template <typename T, typename U>
bool operator==(U lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) == rhs;
}

template <typename T>
bool operator!=(const Modular<T> &lhs, const Modular<T> &rhs) {
  return !(lhs == rhs);
}
template <typename T, typename U>
bool operator!=(const Modular<T> &lhs, U rhs) {
  return !(lhs == rhs);
}
template <typename T, typename U>
bool operator!=(U lhs, const Modular<T> &rhs) {
  return !(lhs == rhs);
}

template <typename T>
bool operator<(const Modular<T> &lhs, const Modular<T> &rhs) {
  return lhs.value < rhs.value;
}

template <typename T>
Modular<T> operator+(const Modular<T> &lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) += rhs;
}
template <typename T, typename U>
Modular<T> operator+(const Modular<T> &lhs, U rhs) {
  return Modular<T>(lhs) += rhs;
}
template <typename T, typename U>
Modular<T> operator+(U lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) += rhs;
}

template <typename T>
Modular<T> operator-(const Modular<T> &lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) -= rhs;
}
template <typename T, typename U>
Modular<T> operator-(const Modular<T> &lhs, U rhs) {
  return Modular<T>(lhs) -= rhs;
}
template <typename T, typename U>
Modular<T> operator-(U lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) -= rhs;
}

template <typename T>
Modular<T> operator*(const Modular<T> &lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) *= rhs;
}
template <typename T, typename U>
Modular<T> operator*(const Modular<T> &lhs, U rhs) {
  return Modular<T>(lhs) *= rhs;
}
template <typename T, typename U>
Modular<T> operator*(U lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) *= rhs;
}

template <typename T>
Modular<T> operator/(const Modular<T> &lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) /= rhs;
}
template <typename T, typename U>
Modular<T> operator/(const Modular<T> &lhs, U rhs) {
  return Modular<T>(lhs) /= rhs;
}
template <typename T, typename U>
Modular<T> operator/(U lhs, const Modular<T> &rhs) {
  return Modular<T>(lhs) /= rhs;
}

template <typename T, typename U>
Modular<T> power(const Modular<T> &a, const U &b) {
  assert(b >= 0);
  Modular<T> x = a, res = 1;
  U p = b;
  while (p > 0) {
    if (p & 1)
      res *= x;
    x *= x;
    p >>= 1;
  }
  return res;
}

template <typename T> string to_string(const Modular<T> &number) {
  return to_string(number());
}

template <typename T>
std::ostream &operator<<(std::ostream &stream, const Modular<T> &number) {
  return stream << number();
}

template <typename T>
std::istream &operator>>(std::istream &stream, Modular<T> &number) {
  typename common_type<typename Modular<T>::Type, int64_t>::type x;
  stream >> x;
  number.value = Modular<T>::normalize(x);
  return stream;
}

/*
using ModType = int;

struct VarMod { static ModType value; };
ModType VarMod::value;
ModType& md = VarMod::value;
using Mint = Modular<VarMod>;
*/

#include <algorithm>
#include <cassert>
#include <numeric>
#include <string>
#include <vector>

namespace atcoder {

namespace internal {

std::vector<int> sa_naive(const std::vector<int> &s) {
  int n = int(s.size());
  std::vector<int> sa(n);
  std::iota(sa.begin(), sa.end(), 0);
  std::sort(sa.begin(), sa.end(), [&](int l, int r) {
    if (l == r)
      return false;
    while (l < n && r < n) {
      if (s[l] != s[r])
        return s[l] < s[r];
      l++;
      r++;
    }
    return l == n;
  });
  return sa;
}

std::vector<int> sa_doubling(const std::vector<int> &s) {
  int n = int(s.size());
  std::vector<int> sa(n), rnk = s, tmp(n);
  std::iota(sa.begin(), sa.end(), 0);
  for (int k = 1; k < n; k *= 2) {
    auto cmp = [&](int x, int y) {
      if (rnk[x] != rnk[y])
        return rnk[x] < rnk[y];
      int rx = x + k < n ? rnk[x + k] : -1;
      int ry = y + k < n ? rnk[y + k] : -1;
      return rx < ry;
    };
    std::sort(sa.begin(), sa.end(), cmp);
    tmp[sa[0]] = 0;
    for (int i = 1; i < n; i++) {
      tmp[sa[i]] = tmp[sa[i - 1]] + (cmp(sa[i - 1], sa[i]) ? 1 : 0);
    }
    std::swap(tmp, rnk);
  }
  return sa;
}

// SA-IS, linear-time suffix array construction
// Reference:
// G. Nong, S. Zhang, and W. H. Chan,
// Two Efficient Algorithms for Linear Time Suffix Array Construction
template <int THRESHOLD_NAIVE = 10, int THRESHOLD_DOUBLING = 40>
std::vector<int> sa_is(const std::vector<int> &s, int upper) {
  int n = int(s.size());
  if (n == 0)
    return {};
  if (n == 1)
    return {0};
  if (n == 2) {
    if (s[0] < s[1]) {
      return {0, 1};
    } else {
      return {1, 0};
    }
  }
  if (n < THRESHOLD_NAIVE) {
    return sa_naive(s);
  }
  if (n < THRESHOLD_DOUBLING) {
    return sa_doubling(s);
  }

  std::vector<int> sa(n);
  std::vector<bool> ls(n);
  for (int i = n - 2; i >= 0; i--) {
    ls[i] = (s[i] == s[i + 1]) ? ls[i + 1] : (s[i] < s[i + 1]);
  }
  std::vector<int> sum_l(upper + 1), sum_s(upper + 1);
  for (int i = 0; i < n; i++) {
    if (!ls[i]) {
      sum_s[s[i]]++;
    } else {
      sum_l[s[i] + 1]++;
    }
  }
  for (int i = 0; i <= upper; i++) {
    sum_s[i] += sum_l[i];
    if (i < upper)
      sum_l[i + 1] += sum_s[i];
  }

  auto induce = [&](const std::vector<int> &lms) {
    std::fill(sa.begin(), sa.end(), -1);
    std::vector<int> buf(upper + 1);
    std::copy(sum_s.begin(), sum_s.end(), buf.begin());
    for (auto d : lms) {
      if (d == n)
        continue;
      sa[buf[s[d]]++] = d;
    }
    std::copy(sum_l.begin(), sum_l.end(), buf.begin());
    sa[buf[s[n - 1]]++] = n - 1;
    for (int i = 0; i < n; i++) {
      int v = sa[i];
      if (v >= 1 && !ls[v - 1]) {
        sa[buf[s[v - 1]]++] = v - 1;
      }
    }
    std::copy(sum_l.begin(), sum_l.end(), buf.begin());
    for (int i = n - 1; i >= 0; i--) {
      int v = sa[i];
      if (v >= 1 && ls[v - 1]) {
        sa[--buf[s[v - 1] + 1]] = v - 1;
      }
    }
  };

  std::vector<int> lms_map(n + 1, -1);
  int m = 0;
  for (int i = 1; i < n; i++) {
    if (!ls[i - 1] && ls[i]) {
      lms_map[i] = m++;
    }
  }
  std::vector<int> lms;
  lms.reserve(m);
  for (int i = 1; i < n; i++) {
    if (!ls[i - 1] && ls[i]) {
      lms.push_back(i);
    }
  }

  induce(lms);

  if (m) {
    std::vector<int> sorted_lms;
    sorted_lms.reserve(m);
    for (int v : sa) {
      if (lms_map[v] != -1)
        sorted_lms.push_back(v);
    }
    std::vector<int> rec_s(m);
    int rec_upper = 0;
    rec_s[lms_map[sorted_lms[0]]] = 0;
    for (int i = 1; i < m; i++) {
      int l = sorted_lms[i - 1], r = sorted_lms[i];
      int end_l = (lms_map[l] + 1 < m) ? lms[lms_map[l] + 1] : n;
      int end_r = (lms_map[r] + 1 < m) ? lms[lms_map[r] + 1] : n;
      bool same = true;
      if (end_l - l != end_r - r) {
        same = false;
      } else {
        while (l < end_l) {
          if (s[l] != s[r]) {
            break;
          }
          l++;
          r++;
        }
        if (l == n || s[l] != s[r])
          same = false;
      }
      if (!same)
        rec_upper++;
      rec_s[lms_map[sorted_lms[i]]] = rec_upper;
    }

    auto rec_sa = sa_is<THRESHOLD_NAIVE, THRESHOLD_DOUBLING>(rec_s, rec_upper);

    for (int i = 0; i < m; i++) {
      sorted_lms[i] = lms[rec_sa[i]];
    }
    induce(sorted_lms);
  }
  return sa;
}

} // namespace internal

std::vector<int> suffix_array(const std::vector<int> &s, int upper) {
  assert(0 <= upper);
  for (int d : s) {
    assert(0 <= d && d <= upper);
  }
  auto sa = internal::sa_is(s, upper);
  return sa;
}

template <class T> std::vector<int> suffix_array(const std::vector<T> &s) {
  int n = int(s.size());
  std::vector<int> idx(n);
  iota(idx.begin(), idx.end(), 0);
  sort(idx.begin(), idx.end(), [&](int l, int r) { return s[l] < s[r]; });
  std::vector<int> s2(n);
  int now = 0;
  for (int i = 0; i < n; i++) {
    if (i && s[idx[i - 1]] != s[idx[i]])
      now++;
    s2[idx[i]] = now;
  }
  return internal::sa_is(s2, now);
}

std::vector<int> suffix_array(const std::string &s) {
  int n = int(s.size());
  std::vector<int> s2(n);
  for (int i = 0; i < n; i++) {
    s2[i] = s[i];
  }
  return internal::sa_is(s2, 255);
}

// Reference:
// T. Kasai, G. Lee, H. Arimura, S. Arikawa, and K. Park,
// Linear-Time Longest-Common-Prefix Computation in Suffix Arrays and Its
// Applications
template <class T>
std::vector<int> lcp_array(const std::vector<T> &s,
                           const std::vector<int> &sa) {
  int n = int(s.size());
  assert(n >= 1);
  std::vector<int> rnk(n);
  for (int i = 0; i < n; i++) {
    rnk[sa[i]] = i;
  }
  std::vector<int> lcp(n - 1);
  int h = 0;
  for (int i = 0; i < n; i++) {
    if (h > 0)
      h--;
    if (rnk[i] == 0)
      continue;
    int j = sa[rnk[i] - 1];
    for (; j + h < n && i + h < n; h++) {
      if (s[j + h] != s[i + h])
        break;
    }
    lcp[rnk[i] - 1] = h;
  }
  return lcp;
}

std::vector<int> lcp_array(const std::string &s, const std::vector<int> &sa) {
  int n = int(s.size());
  std::vector<int> s2(n);
  for (int i = 0; i < n; i++) {
    s2[i] = s[i];
  }
  return lcp_array(s2, sa);
}

// Reference:
// D. Gusfield,
// Algorithms on Strings, Trees, and Sequences: Computer Science and
// Computational Biology
template <class T> std::vector<int> z_algorithm(const std::vector<T> &s) {
  int n = int(s.size());
  if (n == 0)
    return {};
  std::vector<int> z(n);
  z[0] = 0;
  for (int i = 1, j = 0; i < n; i++) {
    int &k = z[i];
    k = (j + z[j] <= i) ? 0 : std::min(j + z[j] - i, z[i - j]);
    while (i + k < n && s[k] == s[i + k])
      k++;
    if (j + z[j] < i + z[i])
      j = i;
  }
  z[0] = n;
  return z;
}

std::vector<int> z_algorithm(const std::string &s) {
  int n = int(s.size());
  std::vector<int> s2(n);
  for (int i = 0; i < n; i++) {
    s2[i] = s[i];
  }
  return z_algorithm(s2);
}

} // namespace atcoder

template <typename T, class F = function<T(const T &, const T &)>>
class SparseTable {
public:
  int n;
  vector<vector<T>> mat;
  F func;

  SparseTable(const vector<T> &a, const F &f) : func(f) {
    n = static_cast<int>(a.size());
    int max_log = 32 - __builtin_clz(n);
    mat.resize(max_log);
    mat[0] = a;
    for (int j = 1; j < max_log; j++) {
      mat[j].resize(n - (1 << j) + 1);
      for (int i = 0; i <= n - (1 << j); i++) {
        mat[j][i] = func(mat[j - 1][i], mat[j - 1][i + (1 << (j - 1))]);
      }
    }
  }

  T get(int from, int to) const {
    assert(0 <= from && from <= to && to <= n - 1);
    int lg = 32 - __builtin_clz(to - from + 1) - 1;
    return func(mat[lg][from], mat[lg][to - (1 << lg) + 1]);
  }
};

constexpr int md = 998244353;
using Mint = Modular<std::integral_constant<decay<decltype(md)>::type, md>>;

struct Value {
  Mint cnt;
  Mint sum_n;
  Mint sum_n_2;
  Value() : cnt(0), sum_n(0), sum_n_2(0) {}
  Value(Mint cnt, Mint sum_n, Mint sum_n_2)
      : cnt(cnt), sum_n(sum_n), sum_n_2(sum_n_2) {}

  Value neg() const { return Value(-cnt, -sum_n, -sum_n_2); }

  void add(const Value &other) {
    cnt += other.cnt;
    sum_n += other.sum_n;
    sum_n_2 += other.sum_n_2;
  }

  void combine(const Value &other) {
    cnt += other.cnt;
    sum_n += other.sum_n + other.cnt;
    sum_n_2 += other.sum_n_2 + 2 * other.sum_n + other.cnt;
  }
};

int main() {
  ios_base::sync_with_stdio(false);
  cin.tie(0);
  string s;
  string t;
  cin >> s >> t;
  int n = s.size();
  int m = t.size();
  string joined = s + "#" + t;
  vector<int> sa = atcoder::suffix_array(joined);
  vector<int> lcp = atcoder::lcp_array(joined, sa);
  auto st = SparseTable(lcp, [&](int x, int y) { return min(x, y); });
  vector<int> rank(joined.size());
  for (int i = 0; i < joined.size(); ++i) {
    rank[sa[i]] = i;
  }
  auto lcp_ids = [&](int sind, int tind) {
    tind += n + 1;
    sind = rank[sind];
    tind = rank[tind];
    if (sind > tind)
      swap(sind, tind);
    return st.get(sind, tind - 1);
  };

  vector<Value> dp(n + 1);
  dp[0].cnt = 1;
  vector<Value> pref_sum(n + 2);

  Value cur_add{};

  for (int i = 0; i <= n; ++i) {
    cur_add.add(pref_sum[i]);
    dp[i].combine(cur_add);
    if (i < n) {
      int max_len = min(m, n - i);
      int pref = lcp_ids(i, 0);
      if (pref < max_len) {
        ++pref;
      }
      if (pref < max_len) {
        pref += lcp_ids(i + pref, pref);
      }
      assert(pref <= max_len);
      pref_sum[i + 1].add(dp[i]);
      pref_sum[i + pref + 1].add(dp[i].neg());
    }
  }
  cout << dp[n].sum_n_2 << '\n';
}