201124861 六、發明說明： 【發明所屬之技術領域】 本申請涉及電腦應用領域，特別是涉及一種搜索結果 生成方法及資訊搜索系統。 【先前技術】 資訊搜索系統是一種能夠爲用戶提供資訊檢索服務的 系統’以網際網路中常用的搜索引擎爲例，作爲應用在網 際網路領域的捜索系統，搜索引擎目前已經成爲用戶上網 必不可少的輔助工具之一。從用戶的角度看，搜索引擎一 般提供一個包含搜索框的頁面，用戶在搜索框輸入關鍵字 或其他搜索條件，藉由瀏覽器提交給搜索引擎後，搜索引 擎就會返回與用戶輸入的關鍵字內容相匹配的資訊。 針對同樣的用戶搜索請求（例如用戶在搜索時所輸入 的搜索關鍵子），搜索引擎往往能夠檢索到多條匹配資訊 ’這個數量可能會達到數十至數萬。而從用戶的角度來講 ，往往只會重點關注在搜索結果中排序比較靠前的資訊。 這樣，在搜索引擎向用戶提供搜索結果時，如何對這些資 訊進行排序就顯得尤爲重要，搜索結果的排序是否合理將 直接影響著用戶的體驗。 搜索引擎在對資訊進行排序時，會對多種因素進行綜 合考慮，參考的因素可以包括資訊來源、資訊可信度、用 戶反饋等等，其中，用戶反饋是影響搜索結果排序的一個 重要因素。例如，當搜索關鍵字爲“中國中央電視臺”時 201124861 ’ 80%的用戶都點擊了中國中央電視臺 ’如果僅從用戶反饋的角度來講，搜索 國中央電視臺的官方主頁排在“中國中 鍵字所對應搜索結果的第一位。 爲達到上述效果，現有技術中，搜 索關鍵字所對應各條匹配資訊的用戶反 根據用戶反饋量由大到小的順序，生成 戶。藉由對現有技術的硏究，發明人發 成方法存在的問題是：對於新發佈的資 値爲0 (或很低），導致其排名靠後， 難被用戶關注到，這樣就一直無法提升 角度講，個別用戶也可以藉由一些作弊 擊）來迅速改變反饋量，從而使自己發 索結果中排名靠前，對他人的正常利益 從用戶的角度來看，現有技術生成的搜 不合理之處，對用戶體驗造成了影響。 【發明內容】 爲解決上述技術問題，本申請提供 成方法及資訊搜索系統，可以將更爲合 '結果展現給用戶，提升用戶體驗，技術 本申請提供一種搜索結果生成方法 資訊搜索系統接收搜索請求，藉由 索請求相匹配的各條匹配資訊； 的官方主頁，那麽 引擎就有理由將中 央電視臺”這個關 索引擎是藉由對搜 饋量進行統計，並 搜索結果提供給用 現現有搜索結果生 訊，反饋量的初始 由於排名靠後又很 排名。而從另一個 手段（例如欺詐點 佈的資訊能夠在搜 造成影響。可見， 索結果排序存在著 了一種搜索結果生 理的匹配資訊排序 方案如下： ，包括： 檢索獲得與所述搜 -6- 201124861 對所述各條匹配資訊的用戶反饋量進行查詢，進一步 計算得到所述各條匹配資訊所屬類別的用戶反饋總量； 根據所述各條匹配資訊所屬類別的用戶反饋總量的大 小，對所述各條匹配資訊進行排序，生成搜索結果。 本申請還提供一種資訊搜索系統，包括： 資訊檢索單元，用於接收搜索請求，藉由檢索獲得與 所述搜索請求相匹配的各條匹配資訊； 用戶反饋量計算單元，用於對各條匹配資訊的用戶反 饋量進行查詢，進一步計算得到每個類別的匹配資訊的用 戶反饋總量； 結果生成單元，用於根據所述各條匹配資訊所屬類別 的用戶反饋總量的大小，對所述各條匹配資訊進行排序， 生成搜索結果。 與現有技術相比，本申請實施例所提供的技術方案， 不是以單條資訊的用戶反饋量大小作爲排序依據，而是以 每條資訊所屬類別的用戶反饋總量的大小作爲排序依據。 這樣，即使是新發佈資訊的用戶反饋量很小’如果其所屬 類別比較受用戶關注，那麽該條資訊同樣有機會排在相對 靠前的位置。從另一個角度來講，單條資訊的用戶反饋量 的增加，並不能直接提高該條資訊的排名’而是提高了該 條資訊所屬類別的排名，因此可以有效地減小欺詐點擊等 作弊手段對搜索結果排序的影響。 201124861 【實施方式】 首先對本申請實施例的一種搜索結果生成方法進行說 明，包括： 資訊搜索系統接收搜索請求，藉由檢索獲得與所述搜 索請求相匹配的各條匹配資訊； 對所述各條匹配資訊的用戶反饋量進行查詢，進一步 計算得到所述各條匹配資訊所屬類別的用戶反饋總量； 根據所述各條匹配資訊所屬類別的用戶反饋總量的大 小，對所述各條匹配資訊進行排序，生成搜索結果。 爲了使本技術領域的人員更好地理解本申請中的技術 方案，下面將結合本申請實施例中的圖式，對本申請實施 例中的技術方案進行清楚、完整地描述，顯然，所描述的 實施例僅僅是本申請一部分實施例，而不是全部的實施例 。基於本申請中的實施例，本領域普通技術人員在沒有做 出創造性勞動前提下所獲得的所有其他實施例，都應當屬 於本申請保護的範圍。 下面以網路搜索應用爲例，對本申請所提供的技術方 案進行詳細說明，圖1所示爲本申請實施例的一種搜索結 果生成方法的流程圖，包括以下步驟： S 1 0 1、搜索引擎接收搜索請求，藉由檢索獲得與所述 搜索請求相匹配的各條匹配資訊； 當用戶需要在網路上搜索資訊時，會輸入—個或爹個 搜索條件，一般最爲常用的搜索條件是搜索關鍵字’根據 具體搜索應用場景的不同，有些搜索引擎還可以支援更多 -8- 201124861 類型的搜索條件，例如資訊發佈時間、資訊屬性等等，本 申請實施例中，將各種搜索條件統稱爲搜索請求。搜索引 擎接收到搜索請求之後，檢索與搜索請求相匹配的資訊。 對應不同的搜索應用場景，檢索到的資訊類型也有所不同 ，例如：在網頁搜索中，檢索到的資訊爲網頁；在電子商 務搜索中，檢索到的資訊爲商品；在文獻搜索中，檢索到 的資訊爲期刊或論文等等。其中，根據搜索請求檢索與之 相匹配的資訊，其實現方法與現有技術相同，本申請實施 例對此不再進行詳細說明。 s 1 0 2、對各條匹配資訊的用戶反饋量進行查詢，進一 步計算得到各條匹配資訊所屬類別的用戶反饋總量； 對應一個搜索請求，搜索引擎往往能夠檢索到多條與 之相匹配的資訊，搜索引擎需要根據一定的原則，對這些 資訊進行篩選、排序，以方便用戶的閱讀。 其中，用戶反饋是影響搜索結果排序的一個重要因素 ，其基本原則是：將用戶最爲關注的資訊排在搜索結果的 最前面。在本申請實施例中，以用戶反饋量作爲反映用戶 對某條資訊關注程度的參數。例如，一個網頁鏈結點擊次 數、鏈結被收藏次數等，能夠直接反映出用戶對這個網頁 的關注程度，因此，對於網頁來說，可以以鏈結點擊次數 、鏈結被收藏次數等資訊作爲用戶反饋量。而在電子商務 中，某個商品的用戶反饋量可以包括：商品成交量、商品 成交金額、商品詢價次數、商品資訊被收藏次數等資訊。 本領域技術人員可以理解的是，可以選擇某一種資訊來表 -9- 201124861 示用戶反饋量，也可以綜合考慮多種資訊來表示用戶反饋 量，例如： 用戶反饋量=商品成交量x〇.3 +被收藏次數χ2、 用戶反饋量=商品成交金額X商品資訊被收藏次數+ 1 〇 g (商品成交量）， 等等。 用戶反饋量一般是被記錄在用戶反饋曰誌中，搜索引 擎藉由讀取用戶反饋日誌，就可以獲得各條匹配資訊所對 應的用戶反饋量。可以理解的是，搜索引擎可以選擇只對 某段時間（例如最近一周、最近一個月等）的用戶反饋曰 誌進行讀取，以適應用戶興趣點的不斷變化。 假設對應某個搜索請求，搜索引擎檢索到4條與之相 匹配的資訊，讀取用戶反饋日誌，得到各條匹配資訊所對 應的用戶反饋量如表1所示： 資訊 用戶反饋量 匹 配 資 訊 1 1 00 匹 配 資 訊 2 30 匹 配 資 訊 3 40 匹 配 資 訊 4 5 表1 由表1可以看出，4條匹配資訊的用戶反饋量大小關 係爲：匹配資訊1 >匹配資訊3>匹配資訊2>匹配資訊4。 如果根據現有技術的方案，也將以這個順序生成搜索結果 ，並最終展現給用戶。而在本申請技術方案中，需要對各 條匹配資訊所對應的用戶反饋量做進一步處理。 -10- 201124861 網際網路中的資訊，很多都是按照一定的類別進行發 佈的’例如’在門戶網站中，網頁類型可以包括新聞、體 育、娛樂、財經等等，在電子商務網站中，商品類別包括 家居、電器、服飾、食品等等。那麽，對於搜索引擎檢索 到的每條匹配資訊，都會對應一個自身所屬的類別。本申 請實施例中’獲得各條匹配資訊所對應的用戶反饋量之後 ’首先查詢各條匹配資訊所屬的類別。對於網頁而言，可 以根據網址的路徑獲知網頁所屬的類別，例如，網址路徑 中包含“ news”欄位的網頁爲新聞類網頁，網址路徑中包 含“sports”欄位的網頁爲體育類網頁，等等；而對於商 品而言，直接查詢其商品資訊就可以獲得該商品所屬的類 別。 還要進一步計算每個類別的匹配資訊的用戶反饋總量 。例如，在表1的例子中，匹配資訊1和匹配資訊4是屬 於“類型A” ’ 匹配資訊2和匹配資訊3是屬於“類型 B” ，則“類型A”的用戶反饋總量爲1 00 + 5 = 1 05、 “類 型B”的用戶反饋總量爲30 + 40 = 70，如表2所示： 類型 用戶反饋總量 類型A 105 類型B 70 表2 S 1 03、根據各條匹配資訊所屬類別的用戶反饋總量的 大小，對各條匹配資訊進行排序，生成搜索結果。 由表2可以看出，“類型A ”比“類型B ”更受用戶 -11 - 201124861 的關注’因此，如果僅從用戶反饋總量的角度考慮，屬於 “類型A”的資訊應該排在屬於“類型B ”的資訊的前面 〇 對於匹配資訊4而言，其用戶反饋量很小，如果應用 現有技術的方案，常規情況下，匹配資訊4將很難獲得靠 前的排名。而本申請的技術方案並不是以單條資訊的用戶 反饋量大小作爲排序依據，匹配資訊4的用戶反饋量雖然 很小，但是由於它屬於比較受到關注的類型，因此在本申 請技術方案所生成的搜索結果中，匹配資訊4將排在匹配 資訊2和匹配資訊3的前面（或者說匹配資訊4將有更多 的機會排在匹配資訊2和匹配資訊3的前面）。這樣，即 使是新發佈的資訊，也有了更多的機會能夠在搜索結果中 獲得比較靠前的排名，更好地適應了用戶的實際需求。 以表1爲基礎，如果有人新發佈了能夠和搜索請求相 匹配的資訊5 (假設該資訊5屬於類型C )，並且藉由欺 詐點擊等手段令其用戶反饋量在短時間內達到5 0，如果 應用現有技術的方案，這條匹配資訊5將直接排在搜索結 果中的第二名，從而影響了其他資訊發佈者的正常利益。 但是，應用本申請的技術方案，由於其所屬類型C的用戶 反饋總量低於類型A和類型B，因此即使藉由作弊手段， 匹配資訊5仍然無法獲得靠前的排名。可以理解的，上述 的例子僅用於示意性說明，在實際應用中，資訊的分類更 多，所檢索到的匹配資訊數量也更大，個別用戶雖然可以 對自己所發佈的一條或幾條資訊採用作弊手段提高反饋量 -12 - 201124861 ’但是無法對資訊所在類別的用戶反饋總量造成太大影響 ，從而有效地減小了作弊對搜索結果排序的影響。 需要說明的是，以上實施例所介紹的，是僅從用戶反 饋量這一角度考慮，對匹配資訊進行排名，在實際的應用 中，搜索引擎在生成搜索結果時，可以對多種因素進行綜 合考慮。一般是將每個因素都作爲一個加權參數，並且根 據這些因素的重要程度，爲每個加權參數設定一個加權係 數，藉由對各個加權參數的加權平均處理，得到一個排序 分値，搜索引擎最終根據各條匹配資訊排序分値的大小， 確定各條匹配資訊在搜索結果中的排列順序》 如果應用現有技術的方案，單條匹配資訊的用戶反饋 量越大，則其所獲得的加權値就越大。而應用本申請的技 術方案，單條匹配資訊所屬類別的用戶反饋總量越大，則 其所獲得的加權値就越大。根據表2所示的結果，匹配資 訊1和匹配資訊4在用戶反饋量這項參數的加權値大於匹 配資訊2和匹配資訊3的加權値。與現有技術相比，匹配 資訊1將有更大的機會獲得比較靠前的排名。 具體而言，可以根據每個類別匹配資訊的用戶反饋總 量的比値，計算得到屬於每個類別的匹配資訊的加權値。 以表2爲例，類型A的用戶反饋總量爲105、類型B的用 戶反饋總量爲70，其比値爲3 : 2。可以進一步對該比値 進行歸一化處理，例如，將每一個類別的用戶反饋總量除 以所有類別的用戶反饋總量之和，所得到的比値爲0.6 : 0.4，那麽0.6和0.4就分別是屬於類別A和類別B的匹 -13- 201124861 配資訊在用戶反饋量這一參數上所獲得的加權値。也可以 將每一個類別的用戶反饋總量除以最大的單類用戶反饋總 量，則所得的比値爲1 : 0.67，那麽1和0.67就分別是屬 於類別A和類別B的匹配資訊在用戶反饋量這一參數上 所獲得的加權値。 搜索引擎也可以對每個類別匹配資訊的用戶反饋總量 進行排序，根據排序結果，得到屬於每個類別的匹配資訊 的加權値。如表3所示： 類型 用戶反饋總量 加權値 類型A 1000 1 類型B 800 0.75 類型C 600 0.5 類型D 500 0.25 類型E 10 0 表3 可見，最終的每個類別資訊所獲得的加權値，只和這 個類別的用戶反饋總量的排列順序有關，與具體的用戶反 饋總量値無關，也就是說，對於屬於類型E的資訊而言， 只有當類型E的用戶反饋總量超過500時，才會獲得更大 的加權値以提升排名，從而能夠進一步減小作弊對搜索結 果排序的影響。 以上介紹了兩種計算加權値的具體例子，根據“單條 匹配資訊所屬類別的用戶反饋總量越大，則其所獲得的加 權値就越大”這一原則，本領域技術人員還可以結合具體 需求，採取其他技術手段來計算加權値，這些也在本申請 -14- 201124861 的保護範圍內。 在實際應用中，對於多種因素的綜合考慮，除了採用 加權的形式之外，還可以採用分級的形式。即：在根據一 個（或多個）因素對匹配資訊進行第一次排序之後，再根 據其他一個或多個因素對第一次排序的結果做第二次排序 〇 針對本申請所提出的技術方案，本領域技術人員容易 想到的是：在根據各條匹配資訊所屬類別的用戶反饋總量 的大小對各條匹配資訊進行排序之後，還可以進一步根據 各條匹配資訊的用戶反饋量大小，對各類別下的匹配資訊 進行排序。 以表1中的資料爲例，應用申請技術方案，可得到“ 屬於類型A的資訊應該排在屬於類型B的資訊的前面” ，即：匹配資訊1和4應排在匹配資訊2和3之前。進一 步地，根據單條匹配資訊的用戶反饋量大小對每個類別下 的匹配資訊進行二次排序，可以得到：匹配資訊1應排在 匹配資訊4之前、匹配資訊3應排在匹配資訊2之前，則 最終的排序結果爲· 匹配資訊4、匹配資訊1、匹配資訊3、匹配資訊2。 可見，上述方案，一方面保證了受關注的類型能夠排 在前面，另一方面，在類型相同的前提下，進一步根據單 f条用戶反饋量的大小，分別對每個類別下的匹配資訊進行 排序。當然，本領域技術人員可以理解的是，在根據各條 匹配資訊所屬類別的用戶反饋總量的大小對各條匹配資訊 -15- 201124861 進行排序之後，也可以根據其他的因素（可是一個或多個 )對各類別下的各條匹配資訊進行排序。並且，如果有必 要，還可以根據其他因素進一步做第三次排序、第四次排 序......，本說明書不再—列舉。 下面將結合幾個具體的應用實例，對本申請的搜索結 果生成方法進行說明。 例如在網頁搜索應用中，以“赤壁”這一關鍵字進行 搜索，搜索引擎會檢索到很多條與“赤壁”匹配的網頁， 這些網頁分別屬於不同類別。藉由讀取某段時間的用戶反 饋曰誌，並根據網頁類別計算每個類別的用戶反饋總量， 得到結果如表4所示： 網頁類型 用戶反饋總量 娛樂 100 軍事 50 歷史 60 旅遊 20 遊戲 3 5 表4 “赤壁”對應的是一場著名的古代戰役，自然有很多 匹配的網頁都是屬於“軍事”、“歷史”類別的；同時“ 赤壁”也經常出現於影視或遊戲情節中，所以也有很多匹 配的網頁是屬於“娛樂”、“遊戲”類別。此外“赤壁” 還是一個旅遊景點，因此，也有一些匹配網頁是屬於“旅 遊”類別。 由於用戶反饋量是藉由讀取某段時間的用戶反饋曰誌 -16- 201124861 獲得’因此可以反映出這段時間的用戶關注焦點。例如， 《赤壁》作爲一部電影，受到大量人的關注，因此，在影 片上映前後的一段時間內，屬於“娛樂”這一類別的匹配 網頁將會多於其他類別，並且有著很高的用戶點擊量，如 表4所示。應用本申請技術方案，如果用戶使用“赤壁” 這一關鍵字進行搜索，那麽屬於“娛樂”這一類別的匹配 網頁，無論其單個網頁的用戶點擊量多少，都將會獲得更 高的加權値，從而在搜索結果中排在比較靠前的位盧，便 於用戶進行點擊瀏覽。 本申請所提供的技術方案，還適用於電子商務的搜索 應用。例如’用戶以關鍵字“筆記本”進行商品搜索，搜 索引擎可能檢索到的商品會涉及筆記本電腦，筆記本電池 、筆記本散熱器’甚至傳統意義上寫字用的筆記本。按照 電子商務網站對商品類別的劃分，筆記本電腦可能屬於“ 筆記本整機”類別，而筆記本電池、筆記本散熱器屬於“ 筆記本配件”類別’至於傳統意義上寫字用的筆記本，則 可能屬於“文化用品”或“辦公用品”類別。藉由對用戶 反饋量的統計，可以發現在現階段，大部分以“筆記本” 爲關鍵字進行搜索的用戶，其真正關注的商品都是筆記本 電腦’那麽，應用本申請技術方案，屬於“筆記本整機’’ 這一類型的商品，都將獲得較高的加權値，從而在搜索結 果中排在比較靠前的位置，便於用戶進行點擊瀏覽，並且 ’對於新發佈的筆記本電腦商品資訊，同樣有機會排在比 較靠前的位置。而對於屬於“文化用品”或“辦公用品’， -17- 201124861 類別的傳統筆記本，即使藉由作弊手段（例如發佈者自己 提高詢價次數、自己對商品資訊多次進行收藏），也無法 針對“筆記本”這一關鍵字提升排名。因爲傳統的筆記本 根本不是大多數搜索“筆記本”的用戶所真正關注的（真 正關注傳統筆記本的用戶會進一步在“文化用品”或“辦 公用品”的範圍進行搜索，與本申請技術方案無關，在此 不做詳細說明），可見，應用本申請技術方案所生成的搜 索結果，其排序更加符合多數用戶的需求，有效提高了用 戶體驗。 以上兩個例子，僅用於示意性說明，實際的網際網路 資訊，可能具有更爲完善的分類層次，例如，在上面的例 子中，“筆記本電池”和“筆記本散熱器”指的都是“筆 記本配件”分類下的單條的商品資訊。而在實際應用中， “筆記本電池”和“筆記本散熱器”也可能是“筆記本配 件”分類下的兩個子類。那麽，應用本申請所提供的技術 方案，這兩個子類也分別具有所對應的用戶反饋總量，如 果用戶是在“筆記本配件”這個範圍內進行搜索’那麽這 兩個子類的商品也將分別獲得不同的加權値。可以理解的 是，如果用戶是在一個最小的分類範圍內進行搜索’那麽 所獲得的搜索結果，就是以該類別下的單條商品資訊的用 戶反饋量大小作爲排序依據的。 以上介紹了本申請技術方案在網頁搜索和電子商務搜 索兩個方面的應用，可以理解的是，這只是本申請技術方 案較佳的兩種實施方式，事實上，本申請技術方案可以應 -18- 201124861 用於各類搜索需求，例如圖書資料庫搜索' 文獻資料庫搜 索等。並且應用範圍也僅不局限於網際網路領域’其他如 單機、區域網路中的搜索，都可以應用本申請所提供的技 術方案。 相應於上面的方法實施例，本申請還提供一種資訊搜 索系統，參見圖2所示，包括： 資訊檢索單元210，用於接收搜索請求，藉由檢索獲 得與所述搜索請求相匹配的各條匹配資訊； 用戶反饋量計算單元220，用於對各條匹配資訊的用 戶反饋量進行查詢，進一步計算得到每個類別的匹配資訊 的用戶反饋總量； 其中，所述用戶反饋總量爲：屬於該類別的匹配資訊 的用戶反饋量之和； 結果生成單元2 3 0，用於根據各條匹配資訊所屬類別 的用戶反饋總量的大小，對各條匹配資訊進行排序，生成 搜索結果。 其中所述用戶反饋量計算單元220，可以藉由讀取特 定時間段的用戶反饋日誌，對各條匹配資訊的用戶反饋量 進行查詢。 參見圖3所示，所述結果生成單元2 3 0，可以包括： 排序分値計算子單元2 3 1，用於以各條匹配資訊所屬 類別的用戶反饋總量的大小作爲加權參數，計算所述各條 匹配資訊的排序分値； [S] 其中’如果第一匹配資訊所屬類別的用戶反饋總量大 -19- 201124861 於第二匹配資訊所屬類別的用戶反饋總量，則所述第一匹 配資訊的加權値大於所述第二匹配資訊的加權値； 結果生成子單元2 3 2，用於根據各條匹配資訊排序分 値的大小，生成搜索結果。 參見圖4所示，所述排序分値計算子單元23 1，可以 包括： 第一加權値計算模組23 1 1，用於根據各條匹配資訊 所屬類別的用戶反饋總量的大小，得到屬於每個類別的匹 配資訊的加權値； 本領域技術人員可以理解，排序分値計算子單元2 3 1 中，還可以進一步包括第二加權値計算模組2 3 1 2、第三 加權値計算模組2 3 1 3……，用於對其他加權參數所對應 的加權値進行計算。 加權平均模組23 1 0，用於對包括所述第一加權値計 算模組的計算結果在內的加權値進行加權平均處理，得到 各條匹配資訊的排序分値。 其中，所述第一加權値計算模組23 1 1，具體可以用 於計算每個類別匹配資訊的用戶反饋總量的比値，根據所 述比値，得到屬於每個類別的匹配資訊的加權値。也可以 對每個類別匹配資訊的用戶反饋總量進行排序，根據排序 結果，得到屬於每個類別的匹配資訊的加權値。 參見圖5所示，所述結果生成單元2 3 0，也可以包括 以下的組成部分： 第一排序子單元2 3 3，用於根據所述各條匹配資訊所 -20- 201124861 屬類別的用戶反饋總量的大小’對所述各條匹配資訊進行 排序； 第二排序子單元2 3 4，用於根據所述各條匹配資訊的 用戶反饋量大小，對各類別下的匹配資訊進行排序。 以上所提供的資訊搜索系統，可以是應用於網際網路 搜索的搜索引擎，也可以是應用於單機、區域網路的搜索 的資訊搜索系統。 當然，用戶反饋量並不一定是對搜索結果排序的唯一 因素。其他因素，例如用戶輸入的關鍵字與網頁所展示資 訊的匹配程度，網頁的Page Rank値等，都可以與用戶反 饋量一起作爲對搜索結果排序的因素。 爲了描述的方便，描述以上裝置時以功能分爲各種單 元分別描述。當然，在實施本申請時可以把各單元的功能 在同一個或多個軟體和/或硬體中實現。 藉由以上的實施方式的描述可知，本領域的技術人員 可以清楚地瞭解到本申請可借助軟體加必需的通用硬體平 臺的方式來實現。基於這樣的理解，本申請的技術方案本 質上或者說對現有技術做出貢獻的部分可以以軟體産品的 形式體現出來，該電腦軟體産品可以儲存在儲存媒體中， 如ROM/RAM、磁碟、光碟等，包括若干指令用以使得一 台電腦設備（可以是個人電腦，伺服器，或者網路設備等 )執行本申請各個實施例或者實施例的某些部分所述的方 法。 本說明書中的各個實施例均採用遞進的方式描述，各 -21 - 201124861 個實施例之間相同相似的部分互相 重點說明的都是與其他實施例的不 統實施例而言，由於其基本相似於 得比較簡單，相關之處參見方法實 以上所描述的系統實施例僅僅是示 分離部件說明的單元可以是或者也 ，作爲單元顯示的部件可以是或者 即可以位於一個地方，或者也可以 。可以根據實際的需要選擇其中的 現本實施例方案的目的。本領域普 造性勞動的情況下，即可以理解並 本申請可用於衆多通用或專用 中。例如：個人電腦、伺服器電腦 備、平板型設備、多處理器系統、 置頂盒、可編程的消費電子設備、 大型電腦、包括以上任何系統或設 等。 本申請可以在由電腦執行的電 下文中描述，例如程式模組。一般 特定任務或實現特定抽象資料類型 元件' 資料結構等等。也可以在分 申請，在這些分散式計算環境中， 接的遠端處理設備來執行任務。在 式模組可以位於包括儲存設備在內 參見即可，每個實施例 同之處。尤其，對於系 方法實施例，所以描述 施例的部分說明即可。 意性的，其中所述作爲 可以不是物理上分開的 也可以不是物理單元， 分佈到多個網路單元上 部分或者全部模組來實 通技術人員在不付出創 實施。 的計算系統環境或配置 、手持設備或攜帶型設 基於微處理器的系統、 網路P C、小型電腦、 備的分散式計算環境等 腦可執行指令的一般上 地，程式模組包括執行 的常式、程式、物件、 散式計算環境中實踐本 由藉由通信網路而被連 分散式計算環境中，程 的本地和遠端電腦儲存 -22- 201124861 媒體中。 以上所述僅是本申請的具體實施方式，應當指出，對 於本技術領域的普通技術人員來說，在不脫離本申請原理 的前提下，還可以做出若干改進和潤飾，這些改進和潤飾 也應視爲本申請的保護範圍。 【圖式簡單說明】 爲了更清楚地說明本申請實施例或現有技術中的技術 方案，下面將對實施例或現有技術描述中所需要使用的圖 式作簡單地介紹，顯而易見地，下面描述中的圖式僅僅是 本申請中記載的一些實施例，對於本領域普通技術人員來 講，在不付出創造性勞動性的前提下，還可以根據這些圖 式獲得其他的圖式。 圖1爲本申請實施例一種搜索結果生成方法的流程圖 » 圖2爲本申請實施例一種資訊搜索系統的結構示意圖 i 圖3爲本申請實施例結果生成單元的結構示意圖； 圖4爲本申請實施例排序分値計算子單元的結構示意 圖； 圖5爲本申請實施例結果生成單元的另一種結構示意 圖。 【主要元件符號說明】 -23- 201124861 2 1 0 :資訊檢索單元 220 :用戶反饋量計算單元 2 3 0 :結果生成單元 231 :排序分値計算子單元 2 3 2 :結果生成子單元 2 3 3 :第一排序子單元 2 3 4 :第二排序子單元 2 3 1 0 :加權平均模組 231 1 :第一加權値計算模組 2 3 1 2 :第二加權値計算模組 2 3 1 3 :第三加權値計算模組 -24-201124861 VI. Description of the Invention: [Technical Field] The present application relates to the field of computer applications, and in particular, to a search result generation method and an information search system. [Prior Art] The information search system is a system that can provide users with information retrieval services. Taking the search engine commonly used in the Internet as an example, as a search system for the Internet, the search engine has become a must for users. One of the essential tools. From the user's point of view, the search engine generally provides a page containing a search box, the user enters a keyword or other search conditions in the search box, and after the browser submits to the search engine, the search engine returns the keyword entered by the user. Information that matches the content. For the same user search request (such as the search key entered by the user during the search), the search engine can often retrieve multiple pieces of matching information. The number may reach tens to tens of thousands. From the user's point of view, it is often only focused on the top-ranking information in the search results. In this way, when the search engine provides search results to users, how to sort the information is particularly important. Whether the ranking of the search results is reasonable will directly affect the user experience. When the search engine sorts the information, it will comprehensively consider various factors. The reference factors may include information sources, information credibility, user feedback, etc. User feedback is an important factor affecting the ranking of search results. For example, when the search keyword is "China Central Television", 201124861 '80% of users clicked on China Central Television'. If only from the perspective of user feedback, the official homepage of the search CCTV is ranked in the "China Central Key" The first bit of the corresponding search result. In order to achieve the above effect, in the prior art, the users of the matching information corresponding to the search keyword generate the household according to the order of the user feedback amount. In fact, the inventor's method of development has the problem that the newly released assets are 0 (or very low), which leads to lower rankings and is hard to be noticed by users, so that it has not been able to improve the perspective. You can quickly change the amount of feedback by using some cheats, so that you can rank yourself in the top of the results. For the normal interests of others, from the user's point of view, the unreasonable search generated by the prior art causes the user experience. [Invention] In order to solve the above technical problem, the present application provides a method and an information search system, which can be more 'The results are presented to the user to enhance the user experience. The present application provides a search result generation method. The information search system receives the search request, and by requesting the matching matching information; the official homepage, then the engine has reason to use CCTV. This keyword-based engine is based on the statistics of the search and the search results are provided to the existing search results. The initial amount of feedback is ranked lower because of the ranking. And from another means (such as fraudulent information can be affected in the search. Visible, the ranking of the results there is a sort of search results physiological matching information sorting scheme as follows:, including: retrieval obtained with the search -6- 201124861 Querying the amount of user feedback of each piece of matching information, and further calculating the total amount of user feedback of the category of the matching information; and determining the total amount of user feedback according to the category of the matching information The present invention further provides an information search system, including: an information retrieval unit, configured to receive a search request, and obtain each matching information that matches the search request by searching; The user feedback amount calculation unit is configured to query the user feedback amount of each piece of matching information, and further calculate the total amount of user feedback of the matching information of each category; the result generating unit is configured to: according to the category of the matching information The total amount of user feedback, sorting the pieces of matching information The technical solution provided by the embodiment of the present application is not based on the size of the user feedback of a single piece of information, but is based on the total amount of user feedback of each category of information. Sort by. In this way, even the amount of feedback from users who post new information is small. 'If the category to which it belongs is more concerned by the user, then the piece of information also has a chance to be in a relatively high position. From another perspective, a single piece of information The increase in the amount of user feedback does not directly increase the ranking of the information, but rather increases the ranking of the category of the information, so it can effectively reduce the impact of fraudulent means such as fraudulent clicks on the ranking of search results. A method for generating a search result according to an embodiment of the present application is as follows: the information search system receives a search request, and obtains, by searching, matching pieces of matching information that match the search request; The amount of user feedback is queried, and the various pieces are further calculated. The total amount of user feedback of the category to which the information belongs; sorting the pieces of matching information according to the total amount of user feedback of the categories to which the matching information belongs, and generating search results. To make the people in the technical field better The technical solutions in the present application are described clearly and completely in conjunction with the drawings in the embodiments of the present application. It is obvious that the described embodiments are only a part of the embodiments of the present application. And not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts should fall within the scope of the present application. The search application is provided as an example, and the technical solution provided by the present application is described in detail. FIG. 1 is a flowchart of a search result generating method according to an embodiment of the present application, including the following steps: S 1 0 1. The search engine receives the search request. Retrieving each piece of matching information that matches the search request; when the user needs to When searching for information on the road, you will enter one or one search condition. The most commonly used search condition is search keyword. 'Depending on the specific search application scenario, some search engines can support more -8- 201124861 type search. Conditions, such as information release time, information attributes, and the like, in the embodiment of the present application, various search conditions are collectively referred to as search requests. After the search engine receives the search request, it retrieves information that matches the search request. The types of information retrieved are different for different search application scenarios. For example, in web search, the retrieved information is a web page; in e-commerce search, the retrieved information is a commodity; in the literature search, the retrieved information is retrieved. Information for journals or papers, etc. The method for retrieving the information according to the search request is the same as that of the prior art, and the embodiment of the present application does not describe the details. s 1 0 2. Querying the amount of user feedback of each matching information, further calculating the total amount of user feedback of each category of matching information; corresponding to a search request, the search engine can often retrieve multiple matching products. Information, search engines need to filter and sort these information according to certain principles to facilitate user reading. Among them, user feedback is an important factor affecting the ranking of search results. The basic principle is to rank the information that users are most concerned about at the top of the search results. In the embodiment of the present application, the user feedback amount is used as a parameter reflecting the user's attention to a certain piece of information. For example, the number of clicks on a webpage link, the number of times a link is bookmarked, etc., can directly reflect the user's attention to the webpage. Therefore, for a webpage, information such as the number of links clicked, the number of times the link is bookmarked, and the like can be used as the webpage. User feedback. In e-commerce, the user feedback of a certain product may include: the volume of the commodity, the amount of the transaction of the commodity, the number of times the commodity is inquired, and the number of times the commodity information is collected. Those skilled in the art can understand that a certain type of information can be selected to display the user feedback amount in Table-9-201124861, and a variety of information can be comprehensively used to indicate the amount of user feedback, for example: User feedback amount = commodity volume x〇.3 +Number of times of collection χ2, User feedback amount = Commodity turnover amount X Product information was collected times + 1 〇g (commodity volume), and so on. The amount of user feedback is generally recorded in the user feedback, and the search engine can obtain the amount of user feedback corresponding to each piece of matching information by reading the user feedback log. It can be understood that the search engine can choose to read only the user feedback messages for a certain period of time (for example, the most recent week, the most recent month, etc.) to adapt to the changing user interest points. Suppose that for a certain search request, the search engine retrieves four matching information, reads the user feedback log, and obtains the user feedback amount corresponding to each matching information as shown in Table 1: Information User Feedback Matching Information 1 1 00 Matching information 2 30 Matching information 3 40 Matching information 4 5 Table 1 It can be seen from Table 1 that the user feedback amount relationship of four matching information is: matching information 1 > matching information 3 > matching information 2 > matching information 4. If the solution according to the prior art is used, the search results will also be generated in this order and finally presented to the user. In the technical solution of the present application, the amount of user feedback corresponding to each piece of matching information needs to be further processed. -10- 201124861 Many of the information in the Internet is published according to certain categories. For example, in the portal, the types of web pages can include news, sports, entertainment, finance, etc. In e-commerce websites, goods Categories include home, appliances, apparel, food, and more. Then, for each matching information retrieved by the search engine, it will correspond to a category to which it belongs. In the embodiment of the present application, after obtaining the user feedback amount corresponding to each piece of matching information, ‘first query the category to which each piece of matching information belongs. For a webpage, the webpage belongs to the category to which the webpage belongs. For example, the webpage containing the "news" field in the webpage path is a news webpage, and the webpage containing the "sports" field in the webpage path is a sports webpage. And so on; for goods, directly query their product information to get the category to which the item belongs. The total amount of user feedback for matching information for each category is further calculated. For example, in the example of Table 1, the matching information 1 and the matching information 4 belong to "type A". The matching information 2 and the matching information 3 belong to "type B", and the total amount of user feedback of "type A" is 1 00. + 5 = 1 05, the total user feedback of “Type B” is 30 + 40 = 70, as shown in Table 2: Type User Feedback Total Type A 105 Type B 70 Table 2 S 1 03, Match information according to each The total amount of user feedback of the category, sorting each piece of matching information, and generating search results. As can be seen from Table 2, "Type A" is more concerned by User -11 - 201124861 than "Type B". Therefore, if it is only from the perspective of the total amount of user feedback, the information belonging to "Type A" should be classified. The front of the "type B" information is small for the matching information 4, and the amount of user feedback is small. If the prior art scheme is applied, it is difficult to obtain the ranking of the matching information 4 under normal circumstances. However, the technical solution of the present application is not based on the size of the user feedback of a single piece of information. Although the amount of user feedback of the matching information 4 is small, since it belongs to a type that is of interest, it is generated by the technical solution of the present application. In the search results, the matching information 4 will be ranked in front of the matching information 2 and the matching information 3 (or the matching information 4 will have more chances in front of the matching information 2 and the matching information 3). In this way, even if it is a newly released information, there are more opportunities to get a higher ranking in the search results, and better adapt to the actual needs of users. Based on Table 1, if someone newly publishes information 5 that matches the search request (assuming that the information 5 belongs to type C), and the user feedback amount reaches 50 in a short time by means of fraudulent clicks, etc. If the prior art solution is applied, the matching information 5 will be ranked directly in the second place in the search results, thereby affecting the normal interests of other information publishers. However, applying the technical solution of the present application, since the total amount of user feedback of the type C belongs to be lower than that of the type A and the type B, even if the information is cheated, the matching information 5 cannot obtain the top ranking. It can be understood that the above examples are only used for illustrative explanation. In practical applications, the information is classified more, and the number of matching information retrieved is also larger. Although individual users can publish one or several pieces of information for themselves. Using cheating means to increase feedback -12 - 201124861 'But it can't affect the total amount of user feedback in the category of information, which effectively reduces the impact of cheating on the ranking of search results. It should be noted that, in the above embodiment, the matching information is ranked only from the perspective of the user feedback amount. In an actual application, the search engine can comprehensively consider various factors when generating the search result. . Generally, each factor is taken as a weighting parameter, and according to the importance degree of these factors, a weighting coefficient is set for each weighting parameter, and a sorting branch is obtained by weighted averaging processing of each weighting parameter, and the search engine finally According to the size of each matching information, the order of the matching information in the search results is determined. If the prior art scheme is applied, the greater the amount of user feedback of the single matching information, the more the weighting 値 obtained. Big. With the technical solution of the present application, the greater the total amount of user feedback of a category of matching information, the greater the weighting 获得 obtained. According to the results shown in Table 2, the weighting 値 of the matching information 1 and the matching information 4 in the user feedback amount is larger than the weighting 匹 of the matching information 2 and the matching information 3. Matching Information 1 will have a greater chance of achieving a higher ranking than the prior art. Specifically, the weighted 匹配 of the matching information belonging to each category can be calculated according to the ratio of the total amount of user feedback of the matching information of each category. Taking Table 2 as an example, the total user feedback of type A is 105, and the total amount of user feedback of type B is 70, and the ratio is 3:2. The comparison can be further normalized, for example, by dividing the total amount of user feedback for each category by the sum of the total user feedback for all categories, and the resulting ratio is 0.6: 0.4, then 0.6 and 0.4. They are the weighted 获得 obtained for the parameters of the user feedback amount for the category-13 and 2011B, respectively. It is also possible to divide the total amount of user feedback for each category by the maximum amount of single-class user feedback, and the resulting ratio is 1: 0.67, then 1 and 0.67 are the matching information belonging to category A and category B, respectively. The amount of feedback obtained on this parameter is weighted 値. The search engine can also sort the total amount of user feedback for each category of matching information, and according to the sorting result, obtain the weighting 匹配 of the matching information belonging to each category. As shown in Table 3: Type User Feedback Total Weighted Type A 1000 1 Type B 800 0.75 Type C 600 0.5 Type D 500 0.25 Type E 10 0 Table 3 shows that the final weighting of each category information is only It is related to the order of the total amount of user feedback in this category, and has nothing to do with the total amount of user feedback, that is, for information belonging to type E, only when the total amount of user feedback of type E exceeds 500. Greater weighting will be obtained to improve rankings, which will further reduce the impact of cheating on the ranking of search results. The above describes two specific examples of calculating the weighting ,. According to the principle that “the greater the total amount of user feedback of the category of the matching information, the greater the weighting 値 obtained,” the person skilled in the art can also combine Requirements, other technical means to calculate the weighting 値, these are also within the scope of protection of this application -14-201124861. In practical applications, a comprehensive consideration of a variety of factors, in addition to the weighted form, can also be used in a hierarchical form. That is, after the first sorting of the matching information according to one (or more) factors, the second sorting result is sorted according to one or more other factors, and the technical solution proposed by the present application is It is easily conceivable by those skilled in the art that after sorting each piece of matching information according to the total amount of user feedback of the categories to which the matching information belongs, the size of the user feedback amount of each piece of matching information may be further Sorting information under the category is sorted. Taking the data in Table 1 as an example, applying the application technical solution, it can be obtained that “the information belonging to type A should be placed in front of the information belonging to type B”, that is, the matching information 1 and 4 should be ranked before the matching information 2 and 3. . Further, the matching information of each category is secondarily sorted according to the amount of user feedback of the single matching information, and it can be obtained that the matching information 1 should be ranked before the matching information 4, and the matching information 3 should be ranked before the matching information 2. The final sorting result is · matching information 4, matching information 1, matching information 3, matching information 2. It can be seen that the above solution ensures that the type of attention can be ranked first. On the other hand, under the premise of the same type, the matching information under each category is further determined according to the size of the feedback of the single f user. Sort. Of course, those skilled in the art can understand that after sorting the matching information -15-201124861 according to the total amount of user feedback of the categories to which the matching information belongs, it may also be based on other factors (but one or more) ()) Sort the matching information under each category. And, if necessary, you can further do the third sorting and the fourth sorting according to other factors... This manual is no longer-listed. The search result generation method of the present application will be described below in conjunction with several specific application examples. For example, in the web search application, the search keyword “Chibi” searches for a number of web pages that match the “Red Wall”, and these web pages belong to different categories. By reading the user feedback for a certain period of time, and calculating the total amount of user feedback for each category based on the page category, the results are shown in Table 4: Page Type User Feedback Total Entertainment 100 Military 50 History 60 Tourism 20 Games 3 5 Table 4 “Red Cliff” corresponds to a famous ancient battle. Naturally, many matching pages belong to the “military” and “historical” categories. At the same time, “Red Cliff” often appears in the film or game plot, so There are also many matching web pages that belong to the "entertainment" and "game" categories. In addition, “Red Cliff” is still a tourist attraction, so there are also some matching pages that belong to the “Travel” category. Since the user feedback is obtained by reading the user feedback for a certain period of time -16-201124861, it can reflect the user's focus during this time. For example, "Red Cliff" as a movie has attracted a lot of people's attention. Therefore, in the period before and after the film is released, there will be more matching pages belonging to the category of "entertainment" than other categories, and there are very high users. Click volume, as shown in Table 4. Applying the technical solution of the present application, if the user searches using the keyword "Red Cliff", the matching webpage belonging to the category of "entertainment" will receive higher weighting regardless of the amount of user clicks of the individual webpage. Therefore, it ranks in the top position in the search results, which is convenient for users to click through. The technical solution provided by the application is also applicable to the search application of e-commerce. For example, 'users search for goods with the keyword "notebook", and the search engine may retrieve items that involve laptops, laptop batteries, notebook coolers, and even traditionally used notebooks. According to the classification of merchandise categories by e-commerce websites, laptops may belong to the category of "laptops", while laptop batteries and notebook coolers belong to the category of "notebook accessories". As for notebooks in the traditional sense, they may belong to "culture". "" supplies" or "office supplies" category. By counting the amount of feedback from users, it can be found that at this stage, most of the users who search by "notebook" as keywords are all the products that are really concerned with laptops. Then, applying the technical solution of the present application, it belongs to "notebooks". This type of merchandise will receive a higher weighted 値, which ranks higher in the search results, making it easier for users to click through and “for the newly released laptop product information, the same There is an opportunity to be in a higher position, and for traditional notebooks belonging to the category of “cultural goods” or “office supplies”, -17- 201124861, even by cheating (for example, the publisher himself raises the number of inquiries and owns the goods) The information was collected several times, and the ranking of the "notebook" keyword could not be improved. Because traditional notebooks are not really concerned by most users who search for "notebooks" (users who really pay attention to traditional notebooks will further search in the scope of "cultural products" or "office supplies", regardless of the technical solution of this application, This is not explained in detail. It can be seen that the search results generated by applying the technical solution of the present application are more consistent with the requirements of most users, and the user experience is effectively improved. The above two examples are only used for illustrative purposes. The actual Internet information may have a more complete classification level. For example, in the above example, “laptop battery” and “notebook cooler” refer to A single item of information under the "notebook accessories" category. In practical applications, “laptop battery” and “notebook cooler” may also be two sub-categories under the “notebook accessories” category. Then, applying the technical solution provided by the application, the two sub-categories respectively have the corresponding total amount of user feedback, and if the user searches in the range of "notebook accessories", then the products of the two sub-categories are also Different weightings will be obtained separately. It can be understood that if the user searches within a minimum classification range, then the search result obtained is based on the size of the user feedback amount of the single item information under the category. The application of the technical solution of the present application in webpage search and e-commerce search is described above. It can be understood that this is only two embodiments of the technical solution of the present application. In fact, the technical solution of the present application can be -18 - 201124861 For various types of search needs, such as book database search 'literature database search, etc. Moreover, the application scope is not limited to the Internet domain, and other technologies such as single-machine and regional network search can apply the technical solutions provided by the present application. Corresponding to the above method embodiment, the present application further provides an information search system, as shown in FIG. 2, including: an information retrieval unit 210, configured to receive a search request, and obtain various items matching the search request by searching The user feedback amount calculation unit 220 is configured to query the user feedback amount of each piece of matching information, and further calculate the total amount of user feedback of the matching information of each category; wherein the total amount of user feedback is: The sum of the user feedback amounts of the matching information of the category; the result generating unit 203 is configured to sort the matching information according to the total amount of user feedback of the categories to which the matching information belongs, and generate a search result. The user feedback amount calculation unit 220 can query the user feedback amount of each piece of matching information by reading the user feedback log of a specific time period. As shown in FIG. 3, the result generating unit 203 may include: a sorting branching sub-unit 2 3 1 for calculating a total amount of user feedback of a category to which each piece of matching information belongs as a weighting parameter. The sorting distribution of each piece of matching information; [S] where 'if the total amount of user feedback of the category of the first matching information is large -19- 201124861, the total amount of user feedback of the category of the second matching information, the first The weighting 値 of the matching information is greater than the weighting 所述 of the second matching information; the result generating sub-unit 2 3 2 is configured to sort the size of the branches according to each piece of matching information to generate a search result. As shown in FIG. 4, the sorting and branching sub-unit 23 1 may include: a first weighting and calculating module 23 1 1 for obtaining a total amount of user feedback according to a category of each matching information. The weighting 匹配 of the matching information of each category; those skilled in the art can understand that the sorting branch computing sub-unit 2 3 1 can further include a second weighting 値 computing module 2 3 1 2, a third weighting 値 computing module Group 2 3 1 3... is used to calculate the weighting 对应 corresponding to other weighting parameters. The weighted average module 23 1 0 is configured to perform weighted averaging processing on the weighted 値 including the calculation result of the first weighted 値 computing module to obtain a sorting score of each piece of matching information. The first weighting and calculating module 23 1 1 may be specifically configured to calculate a ratio of total user feedback of each category of matching information, and according to the comparison, obtain weighting of matching information belonging to each category. value. It is also possible to sort the total amount of user feedback for each category matching information, and according to the sorting result, obtain the weighting 匹配 of the matching information belonging to each category. Referring to FIG. 5, the result generating unit 203 may also include the following components: a first sorting subunit 2 3 3, for users according to the respective matching information information -20- 201124861 genre category The size of the total amount of feedbacks is used to sort the pieces of matching information. The second sorting sub-unit 2 3 4 is configured to sort the matching information in each category according to the amount of user feedback of the pieces of matching information. The information search system provided above may be a search engine applied to Internet search or an information search system applied to search of a single machine or a regional network. Of course, the amount of user feedback is not necessarily the only factor that ranks search results. Other factors, such as the degree to which the keyword entered by the user matches the information displayed on the web page, the Page Rank of the web page, etc., can be used together with the user feedback amount as a factor in ranking the search results. For the convenience of description, the above devices are described in terms of functions and are divided into various units for description. Of course, the functions of each unit can be implemented in the same software or software and/or hardware in the implementation of the present application. As will be apparent from the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of a software plus a necessary universal hardware platform. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product in essence or in the form of a software product, which may be stored in a storage medium such as a ROM/RAM or a disk. A disc or the like includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments of the present application or portions of the embodiments. The various embodiments in the present specification are described in a progressive manner, and the same similar parts between the various embodiments of the present invention are described with respect to the embodiments of the other embodiments. Similar to the simpler, the relevant points refer to the method. The system embodiment described above is merely a unit showing the separate component description. Alternatively, or as well, the component displayed as a unit may be or may be located in one place, or may be. The purpose of the present embodiment can be selected according to actual needs. In the case of general labor in the field, it is understood that the application can be used in a variety of general or special applications. For example: personal computers, server computers, tablet devices, multiprocessor systems, set-top boxes, programmable consumer electronics devices, large computers, including any of the above systems or devices. This application can be described in a computer executed by a computer, such as a program module. General Task-specific or implementation-specific abstract data types Component 'data structures, and so on. It is also possible to apply in a distributed computing environment where the remote processing device is connected to perform tasks. The in-use module can be located in the vicinity of the storage device, and each embodiment is identical. In particular, for a method embodiment, a partial description of the embodiment may be described. Intentional, wherein the acts may not be physically separated or may not be physical units, and may be distributed to some or all of the modules of the plurality of network elements to enable the technicians to implement the implementation. Generally, the computing system environment or configuration, the handheld device or the portable microprocessor-based system, the network PC, the small computer, the distributed computing environment, etc. The practice of the program, the program, the object, and the distributed computing environment is stored in the distributed computing environment by the communication network, and the local and remote computers of the program are stored in the media-22-201124861. The above description is only a specific embodiment of the present application, and it should be noted that those skilled in the art can also make several improvements and retouchings without departing from the principles of the present application. It should be considered as the scope of protection of this application. BRIEF DESCRIPTION OF THE DRAWINGS In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art description will be briefly described below. Obviously, in the following description The drawings are only some of the embodiments described in the present application, and those skilled in the art can obtain other drawings according to these drawings without any inventive labor. 1 is a flow chart of a method for generating a search result according to an embodiment of the present application. FIG. 2 is a schematic structural diagram of an information search system according to an embodiment of the present application. FIG. 3 is a schematic structural diagram of a result generating unit according to an embodiment of the present application; FIG. 5 is a schematic structural diagram of a result generating unit according to an embodiment of the present application. FIG. [Explanation of main component symbols] -23- 201124861 2 1 0 : Information retrieval unit 220: User feedback amount calculation unit 2 3 0 : Result generation unit 231: Sorting division calculation sub-unit 2 3 2 : Result generation sub-unit 2 3 3 : First sorting subunit 2 3 4 : Second sorting subunit 2 3 1 0 : Weighted average module 231 1 : First weighting 値 computing module 2 3 1 2 : Second weighting 値 computing module 2 3 1 3 : Third Weighted 値 Calculation Module-24-