CN114442816A - Association prefetching method and device for association prefetching - Google Patents

Abstract

The embodiment of the application discloses a method and a device for associative prefetching. An embodiment of the method comprises: acquiring input information of a user; sending an association prefetching request under the condition that a preset condition is met so as to obtain a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result; and displaying the target candidate result, and displaying the target association result under the condition that the user screens the target candidate result. The implementation mode solves the problem that the association candidate display process is delayed or jammed, and improves the input efficiency.

Description

Association prefetching method and device for association prefetching

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to an associative prefetching method and device and a device for associative prefetching.

Background

When a user inputs content by using an input method application, association candidates can be provided for the user in an association mode according to the content input by the user, the information such as the above and the like, so that the input cost of the user is saved, and the input efficiency is improved. For example, when the user is "right" on the screen, the association candidates of "class", "back", and the like may be provided.

In the prior art, after a certain candidate item corresponding to information is input on a screen by a user, an association request is sent to a server, so as to obtain an association candidate corresponding to the candidate item. Since the server needs a certain time to process the data and return the data, this approach may cause a delay or a jam in the presentation process of the association candidate, which affects the input efficiency of the user.

Disclosure of Invention

The embodiment of the application provides an association prefetching method and device and a device for association prefetching, and aims to solve the technical problem that in the prior art, an association candidate display process is delayed or jammed.

In a first aspect, an embodiment of the present application provides an associative prefetch method, including: acquiring input information of a user; sending an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met; and displaying the target candidate result, and displaying the target association result under the condition that the user screens the target candidate result.

In a second aspect, an embodiment of the present application provides an associative prefetch apparatus, including: a first acquisition unit configured to acquire input information of a user; the second acquisition unit is configured to send an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met; and the display unit is configured to display the target candidate result and display the target association result under the condition that the user screens the target candidate result.

In a third aspect, an embodiment of the present application provides an apparatus for associative prefetching, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs configured to be executed by the one or more processors include instructions for: acquiring input information of a user; sending an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met; and displaying the target candidate result, and displaying the target association result under the condition that the user screens the target candidate result.

In a fourth aspect, embodiments of the present application provide a computer-readable medium on which a computer program is stored, which when executed by a processor, implements the method as described in the first aspect above.

According to the association prefetching method and device and the association prefetching device, the input information of a user is obtained, and under the condition that the preset condition is met, an association prefetching request is sent to obtain a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result; therefore, the target candidate result is displayed, and the target association result is displayed under the condition that the user screens the target candidate result. Therefore, on one hand, the target association result is prefetched after the input information of the user is obtained, and compared with the mode that the association candidate is obtained by sending a request after the user screens the candidate item, the display process of the association candidate is prevented from being delayed or blocked, and the input efficiency is improved. On the other hand, by setting the preset condition and sending the association prefetch request when the preset condition is met, resource consumption caused by frequently sending the association prefetch request is avoided.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is a flow diagram for one embodiment of a method of associative prefetching according to the present application;

FIG. 2 is an exploded flow diagram of step 102 of the associative prefetch method according to the present application;

FIG. 3 is yet another exploded flow diagram of step 102 of the associative prefetch method according to the present application;

FIG. 4 is a block diagram illustrating an embodiment of an associative prefetch apparatus according to the present application;

FIG. 5 is a block diagram of an apparatus for associative prefetching according to the present application;

FIG. 6 is a schematic diagram of a server in accordance with some embodiments of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Referring to FIG. 1, a flow 100 of one embodiment of a method for associative prefetching according to the present application is shown. The above-mentioned associative prefetch method can be operated in various electronic devices, including but not limited to: a server, 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, a car computer, a desktop computer, a set-top box, an intelligent tv, a wearable device, and so on.

The input method application mentioned in the embodiment of the application can support various input methods. The input method may be an encoding method used for inputting various symbols to electronic devices such as computers and mobile phones, and a user may conveniently input a desired character or character string to the electronic devices using the input method application. It should be noted that, in the embodiment of the present application, in addition to the common chinese input method (such as pinyin input method, wubi input method, zhuyin input method, phonetic input method, handwriting input method, etc.), the input method may also support other languages (such as english input method, japanese hiragana input method, korean input method, etc.), and the input method and the language category of the input method are not limited at all.

The associative prefetch method in this embodiment may include the following steps:

step 101, obtaining input information of a user.

In the present embodiment, the execution subject of the association prefetch method (the electronic apparatus described above) may acquire input information of the user. The input information may be information input by a user through an input method application. The user can input information by any input method. For example, the input method may be a pinyin, a wubi, a stroke, or other encoding input method, or may be a voice input method, and is not limited herein.

As an example, when the user inputs in a pinyin input manner, the input information may refer to an input string, and specifically, may refer to an encoded character string input by the user. For example, if the user wants to input "immediately", the code string input by the pinyin input method may be "mashang". When the user inputs in a voice input manner, the input information may refer to voice input by the user.

And 102, sending an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met.

In this embodiment, after acquiring the input information of the user, the execution main body may detect whether a preset condition is satisfied based on the input information. And under the condition of meeting the preset condition, sending an association prefetching request to the server to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result.

Here, the server may refer to a server that provides support for the input method application, and the server may be a single server or a server cluster composed of a plurality of servers. The type of the server is not limited herein, and may be, for example, a physical server, a cloud server, or the like. The association prefetch request sent to the server may include, but is not limited to, the obtained input information, the above of the input information (e.g., the latest on-screen statement), and the like.

Here, the target candidate result may be parsed by the server based on the input information. The target candidate may be one or more. Each target candidate result may be a candidate corresponding to the input information. For example, if the input information is the input string "zaihabiazhua", the target candidate result may include a candidate "scratch at seaside" obtained by performing phonetic-to-word conversion (i.e., pinyin-to-text) on the input string "zaihabiazhua".

Here, the target candidate result may correspond to one or more target association results. Each target association result may be an association candidate corresponding to the target candidate result. For example, if the target candidate result is "grab at sea", the target association result may include association candidates such as "crab", "small fish", and the like.

Here, the preset condition may refer to a preset condition for transmitting the associative prefetch request. This condition can be set as required. For example, when the current input information is the same as a certain historical input information and it is known from the historical data that the association candidate returned by the server is triggered after the user inputs the historical input information, it can be considered that a preset condition is met, and at this time, an association prefetch request can be sent. For another example, the candidate item corresponding to the current input information and the association candidate item corresponding to the candidate item may be determined using a local thesaurus, and the association prefetch request may be sent when the association candidate item satisfies a certain condition (e.g., the word frequency is greater than a certain preset value, and the probability of being on the screen is greater than a certain preset value).

In some optional implementations of the present embodiment, as shown in fig. 2, the step 102 can be decomposed into the following sub-steps S11 to S12:

and a substep S11 of obtaining a local association result corresponding to the input information.

Here, the local candidate result corresponding to the input information may be first acquired. Wherein, the local candidate result can be obtained by using a local word stock. The local candidates may be one or more. Each local candidate result may be a candidate corresponding to the input information. For example, if the input information is the input string "qingitian", the local candidate results obtained by using the local thesaurus may include "sunny day", "skyscraper day", "sweet and clear", and the like.

Then, a local association result corresponding to the local candidate result can be determined. Here, the local association result may be obtained from a local thesaurus. For each local candidate result, the local association result corresponding to the local candidate result may be the association candidate corresponding to the local candidate result. For example, the local candidate results include "sunny day", "optima", "sweet and clear", and the like, the local association result corresponding to the local association result "sunny day" may be "thunderbolt", the local association result corresponding to the local association result "optima" may be "bar", and the local association result corresponding to the local association result "sweet and clear" may be "delicious" and the like.

And a substep S12, sending the associative prefetch request in case the expected value of the local associative result is greater than or equal to a preset threshold.

Here, the expectation value may be a numerical value for measuring the probability of a local associative result hit. The value can be calculated based on a preset formula or obtained by utilizing historical data statistics. The probability of hitting the local association result may refer to the probability of being displayed on a screen by the user or the probability of being returned as the target association result by the server, and the like.

As an example, the expected value of the local association result may be determined as follows:

first, the above of the input information is obtained.

Second, a first probability of a local candidate hit is determined based on the input information and the above. The first probability of the local candidate result hit may refer to the probability of the local candidate result being on the screen of the user, or may refer to the word frequency of the local candidate result, etc. The first probability may be based on statistics of a large amount of historical data.

For example, if py _ cand _ i represents a local candidate, py represents input information (e.g., an input string), and context represents a context, the first probability of the local candidate hit may be P (py _ cand _ i | py, context), which represents a conditional probability that the local candidate is py _ cand _ i if the input information is py and the context is context. For example, the above is "xiaoming", the input information is the input string "shuo", and the local candidate result "say" corresponding to the input string "shuo" has a first probability of 0.8.

Third, a second probability of a hit of the local association result is determined based on the above and the local candidate result. The second probability of the local association result hit may refer to a probability that the local association result is displayed on a screen of the user, or a probability that the local association result is returned as a target association result by the server, or the like. The second probability may also be based on statistics of a large amount of historical data.

For example, if the local association result of the local candidate py _ cand _ i is represented by asso _ cand _ j, the second probability of the local association result being hit may be P (asso _ cand _ j | context, py _ cand _ i), which represents the probability of the local association result being hit in the case of the local candidate py _ cand _ i on the screen of the user (i.e., in the case of the context and py _ cand _ i being associated). For example, the above is "xiaoming", the input information is the input string "shuo", the local candidate result of the user on the screen is "say", and the second probability of a hit of the local association result asso _ cand _ j "he" is 0.7.

And fourthly, determining the expected value of the local association result based on the first probability and the second probability.

Here, if there is only one local candidate result, a first probability of hit of the local candidate result may be multiplied by a second probability of hit of the local association result, and the resulting product may be taken as an expected value of the local association result (which may be represented as asso _ sum [ i ]). Here, the value of avo _ sum [ i ] is P (py _ cand _ i | py, context) × P (avo _ cand _ j | context, py _ cand _ i).

In the case that there are at least two local candidate results, for each local candidate result, an expected value of the local association result corresponding to the local candidate result may be determined based on a first probability that the local candidate result hits and a second probability that the local association result corresponding to the local candidate result hits (e.g., taking the product of the first probability and the second probability as the expected value). The expected values of the local association results are then summed to obtain the final expected value (which may be expressed as Σ asso _ sum [ i ]).

By sending the association prefetch request through the substeps S11 to the substep S12, the sending of the association prefetch request can be performed under the condition that a preset condition is satisfied, so as to obtain a target association result. By setting the preset condition for sending the association prefetch request, the association prefetch request can be sent when the preset condition is met, and resource waste caused by frequently sending the association prefetch request is avoided.

In some optional implementations of the present embodiment, as shown in fig. 3, the step 102 can be decomposed into the following sub-steps S21 to S23:

and a sub-step S21 of obtaining input related information.

Here, the input related information may include, but is not limited to, at least one of: the context of the input information, the local candidate result of the input information, the local association result of the local candidate result, length information of the local association result, user information, operating system information, input scenario information, and the like.

And a substep S22, inputting the input related information into a pre-trained decision model to obtain a decision result for indicating whether the associative prefetch request needs to be sent.

Here, the model may extract features from the input-related information and process the features to obtain a decision result indicating whether a suggested prefetch request needs to be sent. Here, the decision model may be obtained by pre-training through a machine learning method (e.g., a supervised learning method). And the basic model used for training the decision model may be a classification model, such as a Support Vector Machine (SVM), a Convolutional Neural Network (CNN), and the like.

Optionally, the decision model is obtained by training through the following steps: first, a sample set is obtained. The sample set may include input-related information and annotation information for a plurality of input information samples, and the annotation information may be used to indicate whether a target associated result for the input information sample is being displayed on a screen by a user. And then, inputting the input relevant information into the two-classification model, outputting the labeling information corresponding to the input relevant information as a target of the two-classification model, and training the two-classification model by using a machine learning method to obtain a decision model.

And a substep S23, sending the associative prefetch request in case the decision result indicates that the associative prefetch request needs to be sent.

Sending the associative prefetch request through the above sub-step S21 to sub-step S23 can automatically decide whether to send the associative prefetch request through a decision model. And sending the request under the condition that the decision model decides that the association prefetch request needs to be sent, so that resource waste caused by frequent sending of the association prefetch request is avoided.

And 103, displaying the target candidate result, and displaying the target association result under the condition that the user screens the target candidate result.

In this embodiment, the executing body may display the target candidate result after obtaining the target candidate result corresponding to the input information and the target association result corresponding to the target candidate result.

For example, the target candidate result may be presented as a candidate corresponding to the input information. Meanwhile, other candidate items corresponding to the input information, such as candidate items selected from a local thesaurus, can also be displayed. Therefore, after the input information of the user is acquired, the local candidate result and the target candidate result (such as a candidate result returned by the cloud server) can be displayed at the same time.

In this embodiment, in a case that the user screens the target candidate result, the execution subject may show the target association result corresponding to the target candidate result. For example, a target association result corresponding to the target candidate result may be presented as a new candidate. In addition, after the user selects the target candidate result, the target candidate result can be displayed on a screen.

Because the target association result corresponding to the target candidate result is obtained in advance, the target association result can be quickly displayed after the target candidate result is displayed on a user, and the situations of blocking and time delay are avoided.

According to the method provided by the embodiment of the application, the input information of the user is obtained, and the association prefetching request is sent under the condition that the preset condition is met, so that the target candidate result corresponding to the input information and the target association result corresponding to the target candidate result are obtained; therefore, the target candidate result is displayed, and the target association result is displayed under the condition that the user screens the target candidate result. Therefore, on one hand, the target association result is prefetched after the input information of the user is obtained, and compared with the mode that the association candidate is obtained by sending a request after the user screens the candidate item, the display process of the association candidate is prevented from being delayed or blocked, and the input efficiency is improved. On the other hand, by setting the preset condition and sending the association prefetch request when the preset condition is met, resource consumption caused by frequently sending the association prefetch request is avoided.

With further reference to fig. 4, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of an associative prefetching apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 1, and the apparatus may be applied to various electronic devices.

As shown in fig. 4, the associative prefetch apparatus 400 of the present embodiment includes: a first acquisition unit 401 configured to acquire input information of a user; a second obtaining unit 402, configured to send an association prefetch request to obtain a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result if a preset condition is met; a presentation unit 403 configured to present the target candidate result and present the target association result in a case where the user screens the target candidate result.

In some optional implementations of this embodiment, the second obtaining unit 402 is further configured to: acquiring a local association result corresponding to the input information; and sending the association prefetching request under the condition that the expected value of the local association result is greater than or equal to a preset threshold value.

In some optional implementations of this embodiment, the expected value of the local association result is determined by: acquiring the above of the input information; determining a first probability of hit of said local candidate based on said input information and said above; determining a second probability of hit of the local association result based on the context and the local candidate result; and determining an expected value of the local association result based on the first probability and the second probability.

In some optional implementations of this embodiment, the determining an expected value of the local association result based on the first probability and the second probability includes: under the condition that at least two local candidate results exist, determining an expected value of a local association result corresponding to each local candidate result based on a first probability that the local candidate result hits and a second probability that the local association result corresponding to the local candidate result hits for each local candidate result; and summing the expected values of the local association results to obtain a final expected value.

In some optional implementations of this embodiment, the second obtaining unit 402 is further configured to: acquiring input related information; inputting the input relevant information into a pre-trained decision model to obtain a decision result for indicating whether an associative prefetch request needs to be sent or not; and sending the associative prefetch request under the condition that the decision result indicates that the associative prefetch request needs to be sent.

In some optional implementations of this embodiment, the input related information includes at least one of: the context of the input information, the local candidate result of the input information, the local association result of the local candidate result, the length information of the local association result, the user information, the operating system information, and the input scenario information.

In some optional implementations of this embodiment, the decision model is obtained by training through the following steps: acquiring a sample set, wherein the sample set comprises input related information and marking information of a plurality of input information samples, and the marking information is used for indicating whether a target association result of the input information samples is displayed on a screen by a user; and inputting the input relevant information into a two-classification model, outputting labeling information corresponding to the input relevant information as a target of the two-classification model, and training the two-classification model by using a machine learning method to obtain a decision model.

According to the device provided by the embodiment of the application, the input information of the user is obtained, and the association prefetching request is sent under the condition that the preset condition is met, so that the target candidate result corresponding to the input information and the target association result corresponding to the target candidate result are obtained; therefore, the target candidate result is displayed, and the target association result is displayed under the condition that the user screens the target candidate result. Therefore, on one hand, the target association result is prefetched after the input information of the user is obtained, and compared with the mode that the association candidate is obtained by sending a request after the user screens the candidate item, the display process of the association candidate is prevented from being delayed or blocked, and the input efficiency is improved. On the other hand, by setting the preset condition and sending the association prefetch request when the preset condition is met, resource consumption caused by frequently sending the association prefetch request is avoided.

Fig. 5 is a block diagram illustrating an apparatus 500 for input according to an example embodiment, where the apparatus 500 may be an intelligent terminal or a server. For example, the apparatus 500 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 5, the apparatus 500 may include one or more of the following components: processing component 502, memory 504, power component 506, multimedia component 508, audio component 510, input/output (I/O) interface 512, sensor component 514, and communication component 516.

The processing component 502 generally controls overall operation of the device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 502 may include one or more processors 520 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 502 can include one or more modules that facilitate interaction between the processing component 502 and other components. For example, the processing component 502 can include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.

The memory 504 is configured to store various types of data to support operations at the apparatus 500. Examples of such data include instructions for any application or method operating on device 500, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 504 may be implemented by any type or combination of volatile or non-volatile memory devices 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 or optical disks.

The power supply component 506 provides power to the various components of the device 500. The power components 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 500.

The multimedia component 508 includes a screen that provides an output interface between the device 500 and a 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 an input signal from a 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 boundary 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 508 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 500 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 510 is configured to output and/or input audio signals. For example, audio component 510 includes a Microphone (MIC) configured to receive external audio signals when apparatus 500 is in operating modes, such as call mode, record mode, and voice recognition mode. The received audio signals may further be stored in the memory 504 or transmitted via the communication component 516. In some embodiments, audio component 510 further includes a speaker for outputting audio signals.

The I/O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the device 500. For example, the sensor assembly 514 may detect an open/closed state of the device 500, the relative positioning of the components, such as a display and keypad of the apparatus 500, the sensor assembly 514 may also detect a change in position of the apparatus 500 or a component of the apparatus 500, the presence or absence of user contact with the apparatus 500, orientation or acceleration/deceleration of the apparatus 500, and a change in temperature of the apparatus 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 516 is configured to facilitate communication between the apparatus 500 and other devices in a wired or wireless manner. The apparatus 500 may 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 516 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the aforementioned communication component 516 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 500 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, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 504 comprising instructions, executable by the processor 520 of the apparatus 500 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Fig. 6 is a schematic diagram of a server in some embodiments of the present application. The server 600 may vary significantly due to configuration or performance, and may include one or more Central Processing Units (CPUs) 622 (e.g., one or more processors) and memory 632, one or more storage media 630 (e.g., one or more mass storage devices) storing applications 642 or data 644. Memory 632 and storage medium 630 may be, among other things, transient or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 622 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the server 600.

The server 600 may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input-output interfaces 658, one or more keyboards 656, and/or one or more operating systems 641, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

A non-transitory computer readable storage medium having instructions therein, which when executed by a processor of an apparatus (smart terminal or server) enable the apparatus to perform a method of associative prefetching, the method comprising: acquiring input information of a user; sending an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met; and displaying the target candidate result, and displaying the target association result under the condition that the user screens the target candidate result.

Optionally, the sending the associative prefetch request when the preset condition is met includes: acquiring a local association result corresponding to the input information; and sending an association prefetching request under the condition that the expected value of the local association result is greater than or equal to a preset threshold value.

Optionally, the expected value of the local association result is determined by the following steps: acquiring the input information; determining a first probability of the local candidate result hitting based on the input information and the above; determining a second probability of the local associative result hit based on the above and the local candidate result; determining an expected value of the local associative result based on the first probability and the second probability.

Optionally, the determining an expected value of the local association result based on the first probability and the second probability includes: under the condition that at least two local candidate results exist, determining an expected value of a local association result corresponding to each local candidate result based on a first probability that the local candidate result hits and a second probability that the local association result corresponding to the local candidate result hits for each local candidate result; and summing the expected values of the local association results to obtain a final expected value.

Optionally, the sending the associative prefetch request when the preset condition is met includes: acquiring input related information; inputting the input related information into a pre-trained decision model to obtain a decision result for indicating whether an associative prefetch request needs to be sent or not; and sending the associative prefetch request under the condition that the decision result indicates that the associative prefetch request needs to be sent.

Optionally, the input related information includes at least one of: the context of the input information, the local candidate result of the input information, the local association result of the local candidate result, the length information of the local association result, the user information, the operating system information, and the input scene information.

Optionally, the decision model is obtained by training through the following steps: acquiring a sample set, wherein the sample set comprises input related information and marking information of a plurality of input information samples, and the marking information is used for indicating whether a target association result of the input information samples is displayed on a screen by a user; inputting the input relevant information into a two-classification model, taking the label information corresponding to the input relevant information as the target output of the two-classification model, and training the two-classification model by using a machine learning method to obtain a decision model.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice in the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements 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 application is limited only by the appended claims.

The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

The method, the apparatus and the apparatus for associative prefetch provided by the present application are described in detail above, and a specific example is applied in the present application to illustrate the principle and the implementation manner of the present application, and the above description of the embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (10)

1. A method of associative prefetching, the method comprising:

acquiring input information of a user;

sending an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met;

and displaying the target candidate result, and displaying the target association result under the condition that the user screens the target candidate result.

2. The method according to claim 1, wherein sending the associative prefetch request if a preset condition is met comprises:

acquiring a local association result corresponding to the input information;

and sending an association prefetching request under the condition that the expected value of the local association result is greater than or equal to a preset threshold value.

3. The method of claim 2, wherein the expected value of the local associative result is determined by:

acquiring the input information;

determining a first probability of the local candidate result hitting based on the input information and the above;

determining a second probability of the local associative result hit based on the above and the local candidate result;

determining an expected value of the local associative result based on the first probability and the second probability.

4. The method of claim 3, wherein determining the expected value of the local associative result based on the first probability and the second probability comprises:

under the condition that at least two local candidate results exist, determining an expected value of a local association result corresponding to each local candidate result based on a first probability that the local candidate result hits and a second probability that the local association result corresponding to the local candidate result hits for each local candidate result;

and summing the expected values of the local association results to obtain a final expected value.

5. The method according to claim 1, wherein the sending the associative prefetch request in case of meeting a preset condition comprises:

acquiring input related information;

inputting the input related information into a pre-trained decision model to obtain a decision result for indicating whether an associative prefetch request needs to be sent or not;

and sending the associative prefetch request under the condition that the decision result indicates that the associative prefetch request needs to be sent.

6. The method of claim 5, wherein the input-related information comprises at least one of: the context of the input information, the local candidate result of the input information, the local association result of the local candidate result, the length information of the local association result, the user information, the operating system information, and the input scene information.

7. The method of claim 5, wherein the decision model is trained by:

acquiring a sample set, wherein the sample set comprises input related information and marking information of a plurality of input information samples, and the marking information is used for indicating whether a target association result of the input information samples is displayed on a screen by a user;

inputting the input relevant information into a two-classification model, taking the label information corresponding to the input relevant information as the target output of the two-classification model, and training the two-classification model by using a machine learning method to obtain a decision model.

8. An associative prefetch apparatus, comprising:

a first acquisition unit configured to acquire input information of a user;

the second acquisition unit is configured to send an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met;

and the display unit is configured to display the target candidate result and display the target association result under the condition that the user screens the target candidate result.

9. An apparatus for associative prefetching, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors the one or more programs including instructions for:

acquiring input information of a user;

sending an association prefetching request to acquire a target candidate result corresponding to the input information and a target association result corresponding to the target candidate result under the condition that a preset condition is met;

and displaying the target candidate result, and displaying the target association result under the condition that the user screens the target candidate result.

10. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.

Images