Request processing method, device and device for processing request

Abstract

The embodiment of the present invention provides a request processing method, device and device for processing requests. The method specifically includes: determining real-time input information; determining corresponding request processing information based on input characteristics, a mapping relationship between input information and request processing information, and real-time input characteristics and the real-time input information; the mapping relationship is obtained based on the user's historical input data, and the historical input data includes: historical input characteristics, historical input information and usage information for the request; based on the request processing information, processing the request corresponding to the real-time input information. The embodiment of the present invention can save resources consumed by requests.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a request processing method, device and a device for processing a request. Background Art

[0002] Traditional input methods are limited by the memory capacity and CPU power of local computers, use smaller word libraries and language models, and have limited input accuracy. Cloud input methods are based on cloud computing technology. With the powerful storage and computing power of server clusters, they have unparalleled advantages over traditional input methods: larger and newer word libraries, more advanced language models, and these advantages significantly improve input accuracy.

[0003] Currently, the client can send a request to the cloud, which may include input information such as an input string. The cloud determines the cloud candidate corresponding to the request and then returns the cloud candidate to the client for the user to select.

[0004] The inventors found in the process of implementing the embodiments of the present invention that in order to obtain cloud candidates in a timely manner, once the input information is updated, a request will be sent for the updated input information. However, some cloud candidates corresponding to the requests cannot be used by the user, so the processing of the requests will cause a waste of resources. Summary of the invention

[0005] The embodiments of the present invention provide a request processing method, a device and a device for processing requests, which can save resources consumed by requests.

[0006] In order to solve the above problem, an embodiment of the present invention discloses a request processing method, including:

[0007] Determine real-time input information;

[0008] Determine the corresponding request processing information according to the input feature, the mapping relationship between the input information and the request processing information, and the real-time input feature and the real-time input information; the mapping relationship is obtained according to the user's historical input data, and the historical input data includes: historical input features, historical input information and usage information for the request;

[0009] The request corresponding to the real-time input information is processed according to the request processing information.

[0010] On the other hand, an embodiment of the present invention discloses a request processing device, including:

[0011] A first determining module, used to determine real-time input information;

[0012] a second determination module, configured to determine corresponding request processing information according to input features, a mapping relationship between input information and request processing information, and real-time input features and the real-time input information; the mapping relationship is obtained according to historical input data of the user, and the historical input data includes: historical input features, historical input information, and usage information for the request; and

[0013] A processing module is used to process the request corresponding to the real-time input information according to the request processing information.

[0014] In another aspect, an embodiment of the present invention discloses an apparatus for processing a request, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations:

[0015] Determine real-time input information;

[0016] Determine the corresponding request processing information according to the input feature, the mapping relationship between the input information and the request processing information, and the real-time input feature and the real-time input information; the mapping relationship is obtained according to the user's historical input data, and the historical input data includes: historical input features, historical input information and usage information for the request;

[0017] The request corresponding to the real-time input information is processed according to the request processing information.

[0018] On the other hand, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the device to perform one or more of the request processing methods described above.

[0019] The embodiments of the present invention include the following advantages:

[0020] The embodiment of the present invention analyzes the historical input data of the user to obtain a mapping relationship between input features, input information and request processing information. The request processing information is relevant information for request processing and can provide a basis for processing the request corresponding to the above real-time input information.

[0021] Specifically, the user's usage information for the request during the input process can reflect the effect or effectiveness of the request for the user. The embodiment of the present invention determines the historical input features and historical input information corresponding to the requests that are valid for the user, and the historical input features and historical input information corresponding to the requests that are invalid for the user based on the user's usage information for the request during the input process, so that the rules of the historical input features and historical input information corresponding to the requests that are valid or invalid for the user can be obtained. Furthermore, the mapping relationship of the embodiment of the present invention can reflect the rules of the historical input features and historical input information corresponding to the requests that are valid or invalid for the user, so the accuracy and rationality of the request processing information can be improved. When the request processing information is applied to request processing, the accuracy and rationality of the request processing results can be improved.

[0022] Furthermore, since the embodiment of the present invention may not send a request when determining that the request is invalid for the user, it can filter the request, thereby saving resources consumed by the request. Assuming that the input process specifically includes n input times, such as input time 1, input time 2, ... input time n, the embodiment of the present invention can filter out the requests corresponding to the first i input times, thereby saving resources consumed by the request. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0024] Figure 1 It is a schematic diagram of an application environment of a request processing method according to an embodiment of the present invention;

[0025] Figure 2 is a flowchart of steps of an embodiment of a request processing method of the present invention;

[0026] Figure 3 is a structural block diagram of an input device embodiment of the present invention;

[0027] Figure 4 is a block diagram of an apparatus 800 for processing a request according to the present invention; and

[0028] Figure 5 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0030] In the embodiments of the present invention, a single input process may start from the reception of an input string and end at the display of the candidate item corresponding to the input string. Taking the input process of the input string "nihao" and the displayed content "你好" as an example, when the character "n" is received, this input process starts, and when the display operation of the candidate item "你好" corresponding to the input string "nihao" is received, this input process ends.

[0031] In order to obtain cloud candidates in a timely manner, currently, once an update of the input string is detected during a single input process, a request will be sent for the updated input string. For example, for user A, the target content of a single input is "五道口". Usually, user A inputs the input string corresponding to the target content by pressing keys multiple times. Assume that user A presses keys "w", "u", "d", "a", "o", "k", "o", "u" in sequence. Then, the embodiments of the present invention can detect the update of the input string according to the key operation and send requests for the updated input strings respectively. For example, a request is sent for the updated input string "wu", and the cloud candidate "无" is obtained; another example is that a request is sent for the updated input string "wud", and the cloud candidate "无敌" is obtained. The above cloud candidates are not the target content that user A hopes for. Therefore, the resources consumed by the processing of the above requests are a waste of resources. The resources consumed by the processing of the requests specifically include: the transmission resources consumed by the client to send requests, the resources consumed by the cloud to obtain cloud candidates according to the requests, and the transmission resources consumed by the cloud to send cloud candidates, etc.

[0032] In view of the technical problem of waste of resources caused by the processing of requests, the embodiments of the present invention provide a request processing solution, which may include: determining real-time input information; determining corresponding request processing information according to the input characteristics, the mapping relationship between the input information and the request processing information, and the real-time input characteristics and the real-time input information; the above mapping relationship is obtained based on the historical input data of the user, and the above historical input data specifically includes: historical input characteristics, historical input information, and usage information for requests; processing the requests corresponding to the real-time input information according to the above request processing information.

[0033] In the embodiment of the present invention, the input feature may characterize the features of the user during the input process. The above input feature may reflect the input habits of the user. Different users may have different input habits. For example, some users are accustomed to inputting in units of characters, some users are accustomed to inputting in units of words, and some users are accustomed to inputting in units of words, etc.

[0034] The embodiment of the present invention analyzes the historical input data of the user to obtain a mapping relationship between input features, input information and request processing information. The request processing information is relevant information for request processing and can provide a basis for processing the request corresponding to the above real-time input information.

[0035] Specifically, the user's usage information for the request during the input process can reflect the effect or effectiveness of the request for the user. The embodiment of the present invention determines the historical input features and historical input information corresponding to the requests that are valid for the user, and the historical input features and historical input information corresponding to the requests that are invalid for the user based on the user's usage information for the request during the input process, so that the rules of the historical input features and historical input information corresponding to the requests that are valid or invalid for the user can be obtained. Furthermore, the mapping relationship of the embodiment of the present invention can reflect the rules of the historical input features and historical input information corresponding to the requests that are valid or invalid for the user, thereby improving the accuracy and rationality of the request processing information.

[0036] Furthermore, since the embodiment of the present invention may not send a request when determining that the request is invalid for the user, it can filter the request, thereby saving resources consumed by the request. Assuming that the input process specifically includes: input time 1, input time 2, ... input time n, etc. (n can be a natural number greater than 0) input times, the embodiment of the present invention can filter out the requests corresponding to the first i (i can be a natural number greater than 0) input times, thereby saving resources consumed by the request.

[0037] By applying the embodiment of the present invention, when different users use the same input string for input, since different users usually correspond to different real-time input features, the embodiment of the present invention can use different request processing information for different users, and thus can provide different request processing services.

[0038] For example, user B is an input user with sentence granularity (often inputs and displays on the screen in sentences), and user C is an input user with single-word granularity (when inputting a word, it will be displayed on the screen); assuming the real-time input string is "dan", the request sending service may not be provided to user B, but the request sending service may be provided to user C.

[0039] The request processing method provided by the embodiment of the present invention can be applied to Figure 1In the application environment shown, Figure 1 As shown, the client 100 and the server 200 are located in a wired or wireless network, and the client 100 and the server 200 perform data exchange through the wired or wireless network.

[0040] Optionally, the client 100 can be run on a terminal, which specifically includes but is not limited to: a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a car computer, a desktop computer, a set-top box, a smart TV, a wearable device, etc. The client 100 can correspond to a website or an APP (Application). The client 100 can correspond to an application such as an input method APP and an instant messaging APP.

[0041] The server of the embodiment of the present invention may be a cloud server (cloud). The cloud is a simple, efficient, safe, reliable, and elastically scalable computing service. The resource information in the cloud is dynamic, so that its processing capacity can be elastically scalable.

[0042] The embodiments of the present invention can be applied to input method programs of various input methods such as keyboard symbols, handwriting, and voice. Taking the keyboard symbol input method as an example, the user can input text through a coded string, and the input string can refer to the coded string input by the user. In the field of input methods, for input method programs such as Chinese, Japanese, Korean, or other languages, the input string input by the user can usually be converted into a candidate of the corresponding language. The following is mainly explained by taking Chinese as an example, and other languages ​​such as Japanese and Korean can be referenced to each other. It can be understood that the above-mentioned Chinese input method can include but is not limited to full spelling, simplified spelling, strokes, Wubi, etc., and the embodiments of the present invention do not limit the specific input method program corresponding to a certain language.

[0043] Taking Chinese input as an example, the types of encoded character strings may include: Pinyin string, character string (such as Wubi string, etc.) Taking English input as an example, the types of encoded character strings may include: letter string, etc.

[0044] In actual applications, for the input method of keyboard symbols, the user can input the above input string through a physical keyboard or a virtual keyboard. For example, for a terminal with a touch screen, a virtual keyboard can be set in the input interface to input the input string by triggering the virtual keys included in the above virtual keyboard. Optionally, examples of the above virtual keyboard may include: a 9-key keyboard and a 26-key keyboard. In addition, it can be understood that in addition to the virtual keys corresponding to letters, the above input interface can also be provided with symbol keys, number keys, such as function keys for switching between Chinese and English, or toolbar keys, etc. It can be understood that the embodiment of the present invention does not limit the specific keys included in the input interface.

[0045] According to some embodiments, the input string may include, but is not limited to, a key symbol or a combination of multiple key symbols input by the user through keys. The key symbol may specifically include pinyin, strokes, kana, and the like.

[0046] In the embodiment of the present invention, the candidate may be used to represent one or more characters provided by the input method program to be selected by the user. The candidate may be characters in languages ​​such as Chinese characters, English characters, and Japanese characters, and the candidate may also be a combination of symbols in the form of emoticons, pictures, and the like. The emoticons include but are not limited to pictures composed of lines, symbols, and words. For example, examples of the emoticons may include: “:P”, “:-o”, “:-)”, and the like.

[0047] The cloud candidate may be a candidate provided by the server. The cloud candidate may be a cloud association candidate or a non-cloud association candidate that matches the input information. For example, if the input information is "wudaok", then its corresponding non-cloud association candidate may include "Wudaokou" and the like. For another example, if the input information is "guoqu", then its corresponding cloud association candidate may include "Thank you for your help during this period of time" and the like. It is to be understood that the embodiments of the present invention do not limit the specific cloud candidates and the specific method for determining the cloud candidates.

[0048] Method Embodiment

[0049] Reference Figure 2 , shows a flowchart of a request processing method embodiment of the present invention, which may specifically include the following steps:

[0050] Step 201: Determine real-time input information;

[0051] Step 202: Determine corresponding request processing information according to input features, a mapping relationship between input information and request processing information, and real-time input features and the real-time input information; the mapping relationship may be obtained according to historical input data of the user, and the historical input data specifically includes: historical input features, historical input information, and usage information for the request;

[0052] Step 203: Process the request corresponding to the real-time input information according to the request processing information.

[0053] Figure 2 The method embodiment shown can be executed by a client. It can be understood that the embodiment of the present invention does not limit the specific execution subject of the method embodiment.

[0054] In step 201, the real-time input information may represent the information input in real time during the input process. The real-time input information may include: a real-time input string, or a real-time input string and the context of the real-time input string.

[0055] It can be understood that during an input process, the real-time input information can be updated according to the update of the user's input operation. The embodiment of the present invention can detect the input operation to obtain the real-time input information.

[0056] In step 202, the input feature may characterize the features of the user during the input process. The above input feature may reflect the user's input habits. Different users may have different input habits.

[0057] Optionally, the above input characteristics specifically include at least one of the following characteristics: input speed, screen display speed, input method, input string length and screen display length.

[0058] The input speed may represent the speed of the input operation, which may include the speed of the input key operation. In practical applications, the input speed may be determined based on the first time interval between two adjacent input key operations. For example, the input speed may be obtained based on the average of the first time interval within a preset time period. It is understood that the embodiments of the present invention do not limit the specific input speed.

[0059] The screen display speed may represent the time interval from the completion of the input string input to the screen display operation. The completion of the input string input may be represented according to the last input key operation of the input string, and thus the screen display speed may be determined according to the second time interval between the last input key operation and the screen display operation. For example, the screen display speed may be obtained according to the average of the second time interval within a preset time period. It is to be understood that the embodiment of the present invention does not limit the specific screen display speed.

[0060] Input methods may include: Pinyin, Wubi, voice, or handwriting, etc. Pinyin methods may also include: simplified spelling, full spelling, double spelling, a mixture of simplified spelling and full spelling (such as abbreviation of the last character, full spelling of non-last character, etc.), etc.

[0061] The input string length may represent the length of the input string corresponding to one input. For example, some users are accustomed to inputting in units of characters, some users are accustomed to inputting in units of words, and some users are accustomed to inputting in units of sentences.

[0062] The length of the screen can represent the number of characters that appear on the screen at one time.

[0063] In the embodiment of the present invention, the request processing information is relevant information of the request processing, and can provide a basis for processing the request corresponding to the above-mentioned real-time input information.

[0064] The request processing information may include: whether to send the processing method information corresponding to the request, such as the first processing method information may include: sending the request, and the second processing method information may include: not sending the request.

[0065] Alternatively, the request processing information may include: a sending probability, and the sending probability may be used as a basis for adjusting the sending delay parameter.

[0066] The sending delay parameter may be a delay or wait parameter for sending a request, which may be used to delay processing of a request corresponding to an input key operation. After receiving an input key operation, the request is not sent immediately, but waits for the duration corresponding to the sending delay parameter. After waiting for the duration corresponding to the sending delay parameter, if no further input key operation (i.e., a new input key operation) is received, the request is sent. If another input key operation is received, a delay request is made for the request corresponding to the second input key operation.

[0067] In one embodiment, the sending delay parameter can be determined based on the keystroke speed of users across the network, for example, the sending delay parameter is 200ms. Assume that the speed of users across the network is 500ms. If the user's next operation is a keystroke operation, the delay processing method can filter out some requests. If the user's next operation is a screen operation, there is still 300ms to wait for the cloud candidate to return, reducing the impact on the screen operation.

[0068] In actual applications, if the sending delay parameter is small, it will affect the number of filters requested. If the sending delay parameter is large, the reservation time of cloud candidates is short, making it impossible to return cloud candidates before the user's screen operation. Therefore, an accurate sending delay parameter will be able to achieve a compromise between the number of filters and the reservation time.

[0069] In conventional technology, a uniform sending delay parameter is usually used for each user. The embodiment of the present invention adjusts the sending delay parameter according to the sending probability obtained based on the real-time input feature. Since the real-time input feature may be the input feature corresponding to the real-time user who is inputting, the sending probability obtained based on the real-time input feature can conform to the personalized input habits of the real-time user, and thus the adjusted sending delay parameter can conform to the personalized input habits of the real-time user, thereby improving the accuracy of the adjusted sending delay parameter.

[0070] The embodiment of the present invention analyzes the historical input data of the user to obtain the mapping relationship between the input characteristics, the input information and the request processing information, which is the relevant information of the request processing and can provide a basis for the processing of the request corresponding to the above real-time input information. The user may refer to the user who uses the input method on the Internet, and the user may include some or all users in the entire network.

[0071] The historical input data can represent the input data corresponding to the completed input. For example, the input process A completed by user A includes: user A presses the keys "w", "u", "d", "a", "o", "k", "o", "u" and so on in sequence, and finally "Wudaokou" is displayed on the screen. In this input process A, the request sent and the cloud candidate returned can all be used as components of the historical input data.

[0072] The user's usage information for the request during the input process can reflect the effect or validity of the request for the user. For example, if user A performs a screen-up operation during input process A, then the request corresponding to the screen-up operation can be considered valid for user A, while the request that does not match the screen-up operation is invalid for user A. For example, when sending a request corresponding to the input string "wu" and a request corresponding to "wud", user A did not perform a screen-up operation, so these requests can be considered invalid requests.

[0073] The embodiment of the present invention determines the historical input features and historical input information corresponding to the requests valid to the user, and the historical input features and historical input information corresponding to the requests invalid to the user, based on the usage information of the user for the request during the input process, so that the regularity of the historical input features and historical input information corresponding to the requests valid or invalid to the user can be obtained. Furthermore, the mapping relationship of the embodiment of the present invention can reflect the regularity of the historical input features and historical input information corresponding to the requests valid or invalid to the user, so that the accuracy and rationality of the request processing information can be improved.

[0074] According to one embodiment, the historical input data of the user is analyzed, specifically including: for a specific first historical input feature, determining a first preset condition that the first historical input information corresponding to a valid request needs to meet. In this way, the mapping relationship may include: a mapping relationship between the first historical input feature and the first preset condition. In this case, the real-time input feature may be matched with the first historical input feature to obtain the first preset condition corresponding to the real-time input feature, and then determine whether the real-time input information meets the first preset condition. If so, the first processing method information is obtained, or a larger sending probability may be obtained. For example, the first preset condition may include: the number of syllables included in the input string is greater than or equal to m, and m may be a natural number greater than 0.

[0075] According to another embodiment, the user's historical input data is analyzed, specifically including: for a specific first historical input feature, determining the second preset condition satisfied by the second historical input information corresponding to the invalid request. In this way, the mapping relationship may include: a mapping relationship between the first historical input feature and the second preset condition. In this case, the real-time input feature may be matched with the first historical input feature to obtain the second preset condition corresponding to the real-time input feature, and then determine whether the real-time input information meets the second preset condition. If so, the second processing method information is obtained, or a smaller sending probability may be obtained. For example, the second preset condition may include: the number of syllables included in the input string is less than m.

[0076] In an embodiment of the present invention, whether the corresponding request is valid can be determined based on whether the historical input information corresponds to the completion of the input. For example, if the historical input information corresponds to the completion of the input, the corresponding request is valid, otherwise the corresponding request is invalid. The input completion can be determined by: after the historical input information is input, no input key operation is received, but an on-screen operation is received.

[0077] According to yet another embodiment, a mapping relationship between input features, input information and request processing information may be characterized by a data analyzer.

[0078] Correspondingly, the above method may further include:

[0079] Determine training data based on historical input data; the training data specifically includes: positive sample data and negative sample data; the positive sample data specifically includes: historical input data corresponding to a completed state of an input; the negative sample data specifically includes: historical input data corresponding to an uncompleted state of an input;

[0080] The training data is trained to obtain a mapping relationship between input features, input information and request processing information.

[0081] Taking the above-mentioned input process A as an example, the positive sample data specifically includes: "wudaokou" and its corresponding historical input features; the negative sample data specifically includes: "wudaoko", "wudaok", "wudao", "wuda", "wud", "wu", "w" and other input strings, and their corresponding historical input features.

[0082] In an optional embodiment of the present application, the mathematical model may be trained based on the training data to obtain a data analyzer, which may characterize the mapping relationship between input data (input features and input information) and output data (request processing information). The output data of the data analyzer may include: processing method information or sending probability.

[0083] Mathematical model is a scientific or engineering model constructed by mathematical logic methods and mathematical language. Mathematical model is a mathematical structure that is expressed in general or approximate terms using mathematical language with reference to the characteristics or quantitative dependencies of a certain system of things. This mathematical structure is a relational structure depicted with the help of mathematical symbols. Mathematical model can be one or a group of algebraic equations, differential equations, difference equations, integral equations or statistical equations and their combinations, which quantitatively or qualitatively describe the mutual relationship or causal relationship between the variables of the system. In addition to mathematical models described by equations, there are also models described by other mathematical tools, such as algebra, geometry, topology, mathematical logic, etc. Among them, mathematical models describe the behavior and characteristics of the system rather than the actual structure of the system. Among them, machine learning, deep learning methods and other methods can be used to train mathematical models. Machine learning methods may include: linear regression, decision tree, random forest, etc. Deep learning methods may include: convolutional neural networks (CNN), long short-term memory networks (LSTM), gated recurrent units (GRU), etc.

[0084] In step 203, the request processing information is applied to the processing of the request corresponding to the real-time input information, which can improve the accuracy and rationality of the request processing result.

[0085] The embodiment of the present invention can provide the following technical solution for processing the request corresponding to the above-mentioned real-time input information:

[0086] In technical solution 1, the request corresponding to the real-time input information is processed, specifically including:

[0087] The request processing information includes sending a request, then sending a request corresponding to the real-time input information; or

[0088] If the request processing information includes not sending a request, then the request corresponding to the real-time input information is not sent.

[0089] For example, the data analyzer may output an output result of sending a request or not sending a request. In this case, the request corresponding to the real-time input information may be processed based on the output result.

[0090] Technical Solution 2

[0091] In Technical Solution 2, the request processing information includes the sending probability, and the request corresponding to the real-time input information is processed, specifically including: adjusting the sending delay parameter based on the sending probability; and processing the request corresponding to the real-time input information based on the adjusted sending delay parameter.

[0092] The embodiment of the present invention adjusts the sending delay parameter according to the sending probability obtained based on the real-time input feature. Since the real-time input feature can be the input feature corresponding to the real-time user who is inputting, the sending probability obtained based on the real-time input feature can meet the personalized input habits of the real-time user, and thus the adjusted sending delay parameter can meet the personalized input habits of the real-time user, thereby improving the accuracy of the adjusted sending delay parameter.

[0093] In an optional embodiment of the present invention, there may be a negative relationship between the sending delay parameter and the sending probability. Specifically, the greater the sending probability, the smaller the sending delay parameter; or the smaller the sending probability, the larger the sending delay parameter.

[0094] Accordingly, the above adjustment of the transmission delay parameter specifically includes: reducing the product of the transmission probability and the preset parameter on the basis of the transmission delay parameter to obtain the adjusted transmission delay parameter. The preset parameter can be determined by those skilled in the art according to actual application requirements. For example, the ratio of the preset parameter to the transmission delay parameter before adjustment can be within a preset range, and the preset range can be [1 / 4, 1 / 2], etc. It can be understood that the embodiment of the present invention does not limit the specific preset range.

[0095] It should be noted that after sending the request corresponding to the real-time input information, the returned cloud candidates can be received and displayed for user selection and display on the screen.

[0096] It should also be noted that after completing an input, the historical input data can be updated based on the input data corresponding to the completed input. Furthermore, the above mapping relationship can be updated based on the updated historical input data. For example, the parameters of the mathematical model corresponding to the input analyzer can be updated. Alternatively, the first preset condition or the second preset condition can be updated, etc.

[0097] In summary, the request processing method of an embodiment of the present invention analyzes the user's historical input data to obtain a mapping relationship between input features, input information and request processing information. The request processing information is relevant information for request processing and can provide a basis for processing the request corresponding to the above-mentioned real-time input information.

[0098] Specifically, the user's usage information for the request during the input process can reflect the effect or effectiveness of the request for the user. The embodiment of the present invention determines the historical input features and historical input information corresponding to the requests that are valid for the user, and the historical input features and historical input information corresponding to the requests that are invalid for the user based on the user's usage information for the request during the input process, so that the rules of the historical input features and historical input information corresponding to the requests that are valid or invalid for the user can be obtained. Furthermore, the mapping relationship of the embodiment of the present invention can reflect the rules of the historical input features and historical input information corresponding to the requests that are valid or invalid for the user, so the accuracy and rationality of the request processing information can be improved. When the request processing information is applied to request processing, the accuracy and rationality of the request processing results can be improved.

[0099] Furthermore, since the embodiment of the present invention may not send a request when determining that the request is invalid for the user, it can filter the request, thereby saving resources consumed by the request. Assuming that the input process specifically includes n input times, such as input time 1, input time 2, ... input time n, the embodiment of the present invention can filter out the requests corresponding to the first i input times, thereby saving resources consumed by the request.

[0100] For example, user B is an input user at sentence granularity (usually inputs and displays on the screen in units of sentences), user C is an input user at single-word granularity (usually inputs a word and displays on the screen), and user D is an input user at word granularity (usually inputs a word and displays on the screen); assuming that user B, user C, and user D input the sentence "I am now in Wudaokou" in full spelling and pinyin, the request processing processes corresponding to user B, user C, and user D respectively include:

[0101] User C. When the real-time input string is "wo", a request sending service is provided for User C. After User C enters "我" on the screen and then continues to receive the real-time input string "xian", a request sending service is still provided for User C. After User C enters "现" on the screen and then continues to receive the real-time input string "zai", a request sending service is still provided for User C. After User C enters "在" on the screen and then continues to receive the real-time input string "wu", a request sending service is still provided for User C. After User C enters "五" on the screen and then continues to receive the real-time input string "dao", a request sending service is still provided for User C. After User C enters "道" on the screen and then continues to receive the real-time input string "kou", a request sending service is still provided for User C.

[0102] User D. When the real-time input string is "wo", a request sending service is provided for User D. After User D enters "我" on the screen and then continues to receive the real-time input string "xian", a request sending service is not provided for User D. After receiving the updated real-time input string "xianzai", a request sending service is provided for User D. After User D enters "现在" on the screen and then continues to receive the real-time input string "wu", a request sending service is not provided for User D. After receiving the updated real-time input string "wudao", a request sending service is not provided for User D. After receiving the updated real-time input string "wudaokou", a request sending service is provided for User D.

[0103] User B. When the real-time input string is "wo", a request sending service is not provided for User B. After receiving the updated real-time input string "woxian", a request sending service is not provided for User B. After receiving the updated real-time input string "woxianzai", a request sending service is not provided for User B. After receiving the updated real-time input string "woxianzaiwu", a request sending service is not provided for User B. After receiving the updated real-time input string "woxianzaiwudao", a request sending service is not provided for User B. After receiving the updated real-time input string "woxianzaiwudaokou", a request sending service is provided for User B.

[0104] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of combinations of movement actions. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequences, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the movement actions involved are not necessarily essential for the embodiments of the present invention.

[0105] Device embodiments

[0106] Reference Figure 3 , shows a structural block diagram of an input device embodiment of the present invention, which may specifically include:

[0107] A first determining module 301 is used to determine real-time input information;

[0108] A second determination module 302 is used to determine corresponding request processing information according to input features, a mapping relationship between input information and request processing information, and real-time input features and the real-time input information; the mapping relationship is obtained according to the user's historical input data, and the historical input data includes: historical input features, historical input information, and usage information for the request; and

[0109] The processing module 303 is used to process the request corresponding to the real-time input information according to the request processing information.

[0110] Optionally, the input feature includes at least one of the following features:

[0111] Input speed, screen display speed, input method, input string length and screen display length.

[0112] Optionally, the above device further includes:

[0113] The third determination module is used to determine the training data according to the historical input data; the training data includes: positive sample data and negative sample data; the positive sample data includes: the historical input data corresponding to the completed state of one input; the negative sample data includes: the historical input data corresponding to the uncompleted state of one input;

[0114] The training module is used to train the above training data to obtain the mapping relationship between input features, input information and request processing information.

[0115] Optionally, the processing module 303 includes:

[0116] A first processing module is configured to send a request corresponding to the real-time input information when the request processing information includes sending a request; or

[0117] The second processing module is used for not sending the request corresponding to the real-time input information when the request processing information includes not sending the request.

[0118] Optionally, the processing module 303 includes:

[0119] An adjustment module, used for adjusting the sending delay parameter according to the sending probability;

[0120] The third processing module is used to process the request corresponding to the real-time input information according to the adjusted sending delay parameter.

[0121] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0122] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0123] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0124] An embodiment of the present invention provides a device for processing requests, including a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: determining real-time input information; determining corresponding request processing information based on input characteristics, a mapping relationship between input information and request processing information, and real-time input characteristics and the real-time input information; the mapping relationship is obtained based on historical input data of the user, and the historical input data includes: historical input characteristics, historical input information and usage information for the request; and processing the request corresponding to the real-time input information based on the request processing information.

[0125] Figure 4 8 is a block diagram of an apparatus 800 for processing a request according to an exemplary embodiment. For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0126] Reference Figure 4 , the device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0127] The processing component 802 generally controls the overall operation of the device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0128] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0129] The power supply component 806 provides power to the various components of the device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 800.

[0130] The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0131] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the device 800 is in an operating mode, such as a call mode, a recording mode, and a voice input mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0132] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0133] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800, and the sensor assembly 814 can also detect the position change of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration / deceleration of the device 800, and the temperature change of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0134] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID, Radio Frequency Identification) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0135] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0136] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0137] Figure 5 1 is a schematic diagram of the structure of the server in some embodiments of the present invention. The server 1900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 can be short-term storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server. Furthermore, the central processing unit 1922 can be configured to communicate with the storage medium 1930 and execute a series of instruction operations in the storage medium 1930 on the server 1900.

[0138] The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1958, one or more keyboards 1956, and / or, one or more operating systems 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0139] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to perform Figure 2 The request processing method shown.

[0140] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), the device is enabled to execute a request processing method, the method comprising: determining real-time input information; determining corresponding request processing information based on input characteristics, a mapping relationship between input information and request processing information, and real-time input characteristics and the real-time input information; the mapping relationship is obtained based on the user's historical input data, the historical input data comprising: historical input characteristics, historical input information and usage information for the request; and processing the request corresponding to the real-time input information based on the request processing information.

[0141] The embodiment of the present invention discloses A1, a request processing method, the method comprising:

[0142] Determine real-time input information;

[0143] Determine the corresponding request processing information according to the input feature, the mapping relationship between the input information and the request processing information, and the real-time input feature and the real-time input information; the mapping relationship is obtained according to the user's historical input data, and the historical input data includes: historical input features, historical input information and usage information for the request;

[0144] The request corresponding to the real-time input information is processed according to the request processing information.

[0145] A2. According to the method described in A1, the input feature includes at least one of the following features:

[0146] Input speed, screen display speed, input method, input string length and screen display length.

[0147] A3. The method according to A1, further comprising:

[0148] Determine training data based on historical input data; the training data includes: positive sample data and negative sample data; the positive sample data includes: historical input data corresponding to a completed state of an input; the negative sample data includes: historical input data corresponding to an uncompleted state of an input;

[0149] The training data is trained to obtain a mapping relationship between input features, input information and request processing information.

[0150] A4. According to the method described in A1, the processing of the request corresponding to the real-time input information comprises:

[0151] The request processing information includes sending a request, then sending a request corresponding to the real-time input information; or

[0152] If the request processing information includes not sending a request, then the request corresponding to the real-time input information is not sent.

[0153] A5. According to the method described in A1, the request processing information includes a sending probability, and the processing of the request corresponding to the real-time input information includes:

[0154] Adjusting a transmission delay parameter according to the transmission probability;

[0155] The request corresponding to the real-time input information is processed according to the adjusted sending delay parameter.

[0156] The embodiment of the present invention discloses B6, an input device, comprising:

[0157] A first determining module, used to determine real-time input information;

[0158] a second determination module, configured to determine corresponding request processing information according to input features, a mapping relationship between input information and request processing information, and real-time input features and the real-time input information; the mapping relationship is obtained according to historical input data of the user, and the historical input data includes: historical input features, historical input information, and usage information for the request; and

[0159] A processing module is used to process the request corresponding to the real-time input information according to the request processing information.

[0160] B7. According to the apparatus described in B6, the input feature includes at least one of the following features:

[0161] Input speed, screen display speed, input method, input string length and screen display length.

[0162] B8. The device according to B6, further comprising:

[0163] The third determination module is used to determine the training data according to the historical input data; the training data includes: positive sample data and negative sample data; the positive sample data includes: the historical input data corresponding to the completed state of one input; the negative sample data includes: the historical input data corresponding to the uncompleted state of one input;

[0164] The training module is used to train the training data to obtain a mapping relationship between input features, input information and request processing information.

[0165] B9. According to the device described in B6, the processing module includes:

[0166] A first processing module is configured to send a request corresponding to the real-time input information when the request processing information includes sending a request; or

[0167] The second processing module is configured to, when the request processing information includes not sending a request, not send a request corresponding to the real-time input information.

[0168] B10. According to the device described in B6, the processing module comprises:

[0169] An adjustment module, used for adjusting a transmission delay parameter according to the transmission probability;

[0170] The third processing module is used to process the request corresponding to the real-time input information according to the adjusted sending delay parameter.

[0171] The embodiment of the present invention discloses C11, a device for processing a request, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations:

[0172] Determine real-time input information;

[0173] Determine the corresponding request processing information according to the input feature, the mapping relationship between the input information and the request processing information, and the real-time input feature and the real-time input information; the mapping relationship is obtained according to the user's historical input data, and the historical input data includes: historical input features, historical input information and usage information for the request;

[0174] The request corresponding to the real-time input information is processed according to the request processing information.

[0175] C12. According to the apparatus of C11, the input feature comprises at least one of the following features:

[0176] Input speed, screen display speed, input method, input string length and screen display length.

[0177] C13. The device according to C11, wherein the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0178] Determine training data based on historical input data; the training data includes: positive sample data and negative sample data; the positive sample data includes: historical input data corresponding to a completed state of an input; the negative sample data includes: historical input data corresponding to an uncompleted state of an input;

[0179] The training data is trained to obtain a mapping relationship between input features, input information and request processing information.

[0180] C14. According to the device described in C11, the processing of the request corresponding to the real-time input information includes:

[0181] The request processing information includes sending a request, then sending a request corresponding to the real-time input information; or

[0182] If the request processing information includes not sending a request, then the request corresponding to the real-time input information is not sent.

[0183] C15. According to the device described in C11, the request processing information includes a sending probability, and the processing of the request corresponding to the real-time input information includes:

[0184] Adjusting a transmission delay parameter according to the transmission probability;

[0185] The request corresponding to the real-time input information is processed according to the adjusted sending delay parameter.

[0186] An embodiment of the present invention discloses D16, a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the device to execute the request processing method as described in one or more of A1 to A5.

[0187] Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0188] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0189] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0190] The request processing method, input device and device for processing requests provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A request processing method, characterized in that: The method comprises: Determine real-time input information; Determine the corresponding request processing information according to the input feature, the mapping relationship between the input information and the request processing information, and the real-time input feature and the real-time input information; the mapping relationship is obtained according to the user's historical input data, and the historical input data includes: historical input features, historical input information and usage information for the request; Processing the request corresponding to the real-time input information according to the request processing information; Determine training data based on historical input data; the training data includes: positive sample data and negative sample data; the positive sample data includes: historical input data corresponding to a completed state of an input; the negative sample data includes: historical input data corresponding to an uncompleted state of an input; The training data is trained to obtain a mapping relationship between input features, input information and request processing information.

2. The method according to claim 1, characterized in that The input feature includes at least one of the following features: Input speed, screen display speed, input method, input string length and screen display length.

3. The method according to claim 1, characterized in that The processing of the request corresponding to the real-time input information includes: The request processing information includes sending a request, then sending a request corresponding to the real-time input information; or If the request processing information includes not sending a request, then the request corresponding to the real-time input information is not sent.

4. The method according to claim 1, characterized in that The request processing information includes a sending probability, and the processing of the request corresponding to the real-time input information includes: Adjusting a transmission delay parameter according to the transmission probability; The request corresponding to the real-time input information is processed according to the adjusted sending delay parameter.

5. An input device, characterized in that: include: A first determining module, used to determine real-time input information; A second determination module, configured to determine corresponding request processing information according to the input feature, the mapping relationship between the input information and the request processing information, and the real-time input feature and the real-time input information; The mapping relationship is obtained based on the user's historical input data, wherein the historical input data includes: historical input features, historical input information, and usage information for the request; and A processing module, used for processing the request corresponding to the real-time input information according to the request processing information; The third determination module is used to determine the training data according to the historical input data; the training data includes: positive sample data and negative sample data; the positive sample data includes: the historical input data corresponding to the completed state of one input; the negative sample data includes: the historical input data corresponding to the uncompleted state of one input; The training module is used to train the training data to obtain a mapping relationship between input features, input information and request processing information.

6. The device according to claim 5, characterized in that The input feature includes at least one of the following features: Input speed, screen display speed, input method, input string length and screen display length.

7. A device for processing a request, characterized in that The system comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: Determine real-time input information; Determine corresponding request processing information according to the input characteristics, the mapping relationship between the input information and the request processing information, and the real-time input characteristics and the real-time input information; The mapping relationship is obtained based on the user's historical input data, and the historical input data includes: historical input features, historical input information and usage information for the request; Processing the request corresponding to the real-time input information according to the request processing information; Determine training data based on historical input data; the training data includes: positive sample data and negative sample data; the positive sample data includes: historical input data corresponding to a completed state of an input; the negative sample data includes: historical input data corresponding to an uncompleted state of an input; The training data is trained to obtain a mapping relationship between input features, input information and request processing information.

8. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, cause an apparatus to perform a request processing method as claimed in one or more of claims 1 to 4.

Images