Codeforces-822D Winter is here(DP)

本文介绍了一个算法问题,模拟《权力的游戏》中约翰·雪诺评估其军队实力的方式。通过定义特定的士兵族群及其强度,该算法需计算所有可能族群的总强度,并输出一个巨大的数值模10^9 + 7的结果。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

D. Winter is here
time limit per test
3 seconds
memory limit per test
256 megabytes
input
standard input
output
standard output

Winter is here at the North and the White Walkers are close. John Snow has an army consisting of n soldiers. While the rest of the world is fighting for the Iron Throne, he is going to get ready for the attack of the White Walkers.

He has created a method to know how strong his army is. Let the i-th soldier’s strength be ai. For some k he calls i1, i2, ..., ik a clan ifi1 < i2 < i3 < ... < ik and gcd(ai1, ai2, ..., aik) > 1 . He calls the strength of that clan k·gcd(ai1, ai2, ..., aik). Then he defines the strength of his army by the sum of strengths of all possible clans.

Your task is to find the strength of his army. As the number may be very large, you have to print it modulo 1000000007 (109 + 7).

Greatest common divisor (gcd) of a sequence of integers is the maximum possible integer so that each element of the sequence is divisible by it.

Input

The first line contains integer n (1 ≤ n ≤ 200000) — the size of the army.

The second line contains n integers a1, a2, ..., an (1 ≤ ai ≤ 1000000) — denoting the strengths of his soldiers.

Output

Print one integer — the strength of John Snow's army modulo 1000000007 (109 + 7).

Examples
input
3
3 3 1
output
12
input
4
2 3 4 6
output
39
Note

In the first sample the clans are {1}, {2}, {1, 2} so the answer will be 1·3 + 1·3 + 2·3 = 12



#include<bits/stdc++.h>
#define lson l,m,rt<<1
#define rson m+1,r,rt<<1|1
#define x first
#define y second
using namespace std;
typedef long long LL;
typedef pair<int, int> PII;
const int MX = 5e6 + 5;
const LL mod = 1e9 + 7;
int a[MX], arr[MX];
void init() {
    for (int i = 2; i < MX; i++) {
        if (!a[i]) {
            for (int j = i + i; j < MX; j += i) {
                a[j] = 1;
                if (!arr[j]) arr[j] = i;
            }
        }
    }
}
LL pow(LL a, LL b) {
    LL ret = 1;
    while (b) {
        if (b & 1) ret = ret * a % mod;
        a = a * a % mod;
        b >>= 1;
    }
    return ret;
}
LL f[MX];
int main() {
    LL t;
    int l, r;
    init();
    //freopen("in.txt", "r", stdin);
    scanf("%I64d%d%d", &t, &l, &r);
    for (int i = 2; i <= r; i++) {
        if (!arr[i]) f[i] = ((LL)i * (i - 1) % mod) * pow(2ll, mod - 2) % mod;
        else f[i] = (f[i / arr[i]] + f[arr[i]] * i / arr[i]) % mod;
    }
    LL ans = 0, k = 1;
    for (int i = l; i <= r; i++) {
        ans = (ans + k * f[i]) % mod;
        k = k * t % mod;
    }
    printf("%I64d\n", ans);
    return 0;
}


引用\[1\]中提到了一种树形动态规划的方法来解决CodeForces - 982C问题。在这个问题中,subtree指的是子连通块,而不是子树。为了使cnt_white - cnt_black尽可能大,可以使用两次树形动态规划来求解。第一次是自底向上的过程,维护一个dp数组,表示以每个节点为根的子树中的最大连通块。第二次是自顶向下的过程,处理自底向上过程中无法包含的树链所代表的子树。在第二次遍历中,需要维护一个sum变量,用于存储树链所代表的子树的贡献。根据ans\[u\]的正负,决定是否能对相邻的子节点做出贡献。如果ans\[u\]为正,则减去dp\[v\]就是树链所代表的子树的权值。最终,ans\[u\]代表包含节点u在内的子连通块的最大权值。\[1\] 问题: CodeForces - 982C 树形DP是什么问题?如何解决? 回答: CodeForces - 982C是一个树形动态规划问题。在这个问题中,需要求解子连通块的最大权值和,使得cnt_white - cnt_black尽可能大。解决这个问题的方法是使用两次树形动态规划。第一次是自底向上的过程,维护一个dp数组,表示以每个节点为根的子树中的最大连通块。第二次是自顶向下的过程,处理自底向上过程中无法包含的树链所代表的子树。在第二次遍历中,需要维护一个sum变量,用于存储树链所代表的子树的贡献。根据ans\[u\]的正负,决定是否能对相邻的子节点做出贡献。最终,ans\[u\]代表包含节点u在内的子连通块的最大权值。\[1\] #### 引用[.reference_title] - *1* *2* [CodeForces - 1324F Maximum White Subtree(树形dp)](https://blog.youkuaiyun.com/qq_45458915/article/details/104831678)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^koosearch_v1,239^v3^insert_chatgpt"}} ] [.reference_item] [ .reference_list ]
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值