CN111125523B

CN111125523B - Searching method, searching device, terminal equipment and storage medium

Info

Publication number: CN111125523B
Application number: CN201911328504.5A
Authority: CN
Inventors: 彭璐; 赵安; 于超
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2019-12-20
Filing date: 2019-12-20
Publication date: 2024-03-01
Anticipated expiration: 2039-12-20
Also published as: WO2021120875A1; CN111125523A

Abstract

The application is applicable to the technical field of computers, and provides a search method, a search device, a search terminal device and a search storage medium based on artificial intelligence (Artificial Intelligence, AI), wherein the search method comprises the following steps: acquiring search keywords; determining a target search object corresponding to the search keyword according to a pre-established mapping relation list of the search object and the search keyword; and displaying the target search object. The mapping relation list of the search object and the search keyword is established according to the historical search behavior and the operation behavior after the historical search behavior. According to the searching method, the target searching object corresponding to the searching keyword is determined through the mapping relation list of the searching object and the searching keyword, and therefore more accurate searching objects can be recommended for users.

Description

Searching method, searching device, terminal equipment and storage medium

Technical Field

The application belongs to the technical field of computers, and particularly relates to a search method, a search device, terminal equipment and a storage medium based on artificial intelligence (Artificial Intelligence, AI).

Background

In the existing terminal equipment, after a user inputs a search keyword, a search result is recommended to the user, so that the user can conveniently and quickly find a corresponding service. However, the existing search method mainly returns a search result according to the matching degree of the names of the search objects and the search keywords input by the user, and cannot accurately recommend some search objects with names not matched with the search keywords, so that the existing search method cannot accurately judge the real search intention of the user.

Disclosure of Invention

The embodiment of the application provides a searching method, a searching device, terminal equipment and a storage medium, so as to accurately judge the actual searching intention of a user.

In a first aspect, an embodiment of the present application provides a search method, including:

acquiring search keywords;

determining a target search object corresponding to a search keyword according to a pre-established mapping relation list of the search object and the search keyword; the mapping relation list of the search object and the search keyword is established according to historical search behaviors and operation behaviors after the historical search behaviors;

and displaying the target search object.

In the embodiment of the application, the mapping relation list of the search object and the search keyword is established according to the historical search behavior and the operation behavior after the historical search behavior, and the actual search intention of the user is reflected by the operation behavior after the historical search behavior, so that when the terminal equipment acquires the search keyword, the target search object is determined according to the mapping relation list of the search object and the search keyword, and more accurate objects can be recommended for the user, and the user experience is improved.

In a possible implementation manner of the first aspect, the mapping relationship list between the search object and the search keyword is established in the following manner:

And acquiring search behavior log information and operation behavior log information of the user, wherein the search behavior log information comprises historical search behaviors, and the operation behavior log information comprises historical operation behaviors. Acquiring a search keyword from the search behavior log information, acquiring an operation behavior in a preset time interval after a user inputs the search keyword from the operation behavior log information, and taking an operation object corresponding to the operation behavior as an initial search object; and calculating the confidence score of the initial search object, wherein the confidence score reflects the association degree of the initial search object and the search keyword, and establishing a mapping relation list of the search object and the search keyword according to the confidence score of the initial search object, so that the initial search object with high association with the search keyword is recommended to a user, and the accuracy of recommendation is improved.

In a possible implementation manner of the first aspect, the calculating a confidence score of the initial search object includes:

and acquiring at least one behavior characteristic value of the initial search object from the operation behavior log information, wherein the behavior characteristic value comprises the use times of the initial search object, the average use time length of the initial search object and/or the use time ratio of the initial search object. And calculating the confidence score of the initial search object according to the at least one behavior characteristic value and the preset weight coefficient corresponding to each behavior characteristic value. Because the behavior characteristic values represent the information of the initial search object operated by the user, the preset weight coefficient reflects the importance degree of each behavior characteristic value, and the confidence score of the initial search object calculated by the behavior characteristic values and the preset weight coefficient corresponding to each behavior characteristic value reflects the intention of the user on the initial search object when searching.

and calculating the confidence score of the initial search object according to the search keyword, the initial search object and a preset prediction model, wherein the preset prediction model is obtained by training a learning model by taking the search keyword, the initial search object corresponding to the search keyword and the confidence score as training samples and adopting a machine learning or deep learning algorithm. The preset prediction model can be reused, and the confidence score of the initial search object is calculated by adopting the preset prediction model, so that the stability of a calculation result is ensured.

In a possible implementation manner of the first aspect, the establishing a mapping relationship list between the search object and the search keyword according to the confidence score of the initial search object includes:

calculating a weight value of the search keyword according to the confidence score of the initial search object;

and establishing a mapping relation list of the search object and the search keywords according to the weight values of the search keywords. It will be appreciated that each search object corresponds to a plurality of search keywords, there may be the same search keywords between different search objects, and different search keywords may have different weight values for different search objects.

In a possible implementation manner of the first aspect, the calculating a weight value of the search keyword according to the confidence score of the initial search object includes:

converting the confidence score of the initial search object into a confidence score of a search keyword;

and taking the confidence score of the search keyword which is larger than a preset confidence threshold as the weight value of the search keyword.

The method includes the steps of obtaining a weight value of a search keyword, arranging the search keywords corresponding to each search object in a descending order according to the weight value of the search keyword, and then taking a preset number of records to obtain a mapping relation list of the search object and the search keyword.

In a possible implementation manner of the first aspect, the determining a target search object corresponding to the search keyword includes:

and taking the search object corresponding to the search keyword with the weight value larger than the preset weight threshold as the target search object, for example, arranging the search objects in descending order according to the weight value, and displaying the arranged search object on the terminal equipment.

In a possible implementation manner of the first aspect, before the acquiring a search keyword from the search behavior log information, the method further includes:

Preprocessing the search behavior log information and the operation behavior log information respectively to obtain preprocessed target search behavior log information and target operation behavior log information;

correspondingly, acquiring a search keyword from the search behavior log information, and acquiring the operation behavior in a preset time interval after the user inputs the search keyword from the operation behavior log information, wherein the operation behavior comprises the following steps:

and acquiring a search keyword from the target search behavior log information, and acquiring the operation behavior in a preset time interval after the user inputs the search keyword from the target operation behavior log information, so that effective log information is obtained, and the accuracy of a calculation result is ensured.

In a possible implementation manner of the first aspect, after the acquiring, from the operation behavior log information, an operation behavior within a preset time interval after the user inputs the search keyword, the method further includes:

deleting the operation behaviors with the operation frequency larger than a first threshold value from the acquired operation behaviors and deleting the operation behaviors with the operation frequency smaller than a second threshold value to obtain effective operation behaviors;

correspondingly, taking the operation object corresponding to the operation behavior as an initial search object comprises the following steps:

And taking the operation object corresponding to the effective operation behavior as an initial search object, thereby preventing the interference of high-frequency operation and low-frequency operation on the calculation result and ensuring the accuracy of the calculation result.

In a second aspect, an embodiment of the present application provides a search apparatus, including:

the acquisition module is used for acquiring the search keywords;

the determining module is used for determining a target search object corresponding to the search keyword according to a pre-established mapping relation list of the search object and the search keyword; the mapping relation list of the search object and the search keyword is established according to historical search behaviors and operation behaviors after the historical search behaviors;

and the display module is used for displaying the target search object.

In a possible implementation manner of the second aspect, the search device further includes a mapping relation establishment module, where the mapping relation establishment module includes:

the acquisition unit is used for acquiring search behavior log information and operation behavior log information of the user;

the extraction unit is used for acquiring search keywords from the search behavior log information, acquiring operation behaviors in a preset time interval after a user inputs the search keywords from the operation behavior log information, and taking an operation object corresponding to the operation behaviors as an initial search object;

A calculation unit for calculating a confidence score of the initial search object;

and the establishing unit is used for establishing a mapping relation list of the search object and the search keyword according to the confidence score of the initial search object.

In a possible implementation manner of the second aspect, the computing unit is specifically configured to:

acquiring at least one behavior characteristic value of the initial search object from the operation behavior log information;

and calculating the confidence score of the initial search object according to the at least one behavior characteristic value and the preset weight coefficient corresponding to each behavior characteristic value.

In a possible implementation manner of the second aspect, the behavior feature value includes a usage number of the initial search object, an average usage duration of the initial search object, and/or a usage number duty ratio of the initial search object.

and calculating the confidence score of the initial search object according to the search keyword, the initial search object and a preset prediction model, wherein the preset prediction model is obtained by training a learning model by taking the search keyword, the initial search object corresponding to the search keyword and the confidence score as training samples and adopting a machine learning or deep learning algorithm.

In a possible implementation manner of the second aspect, the establishing unit is specifically configured to:

and establishing a mapping relation list of the search object and the search keywords according to the weight values of the search keywords.

In a possible implementation manner of the second aspect, the establishing unit is further configured to:

In a possible implementation manner of the second aspect, the determining module is specifically configured to:

and taking the search object corresponding to the search keyword with the weight value larger than the preset weight threshold as the target search object.

In a possible implementation manner of the second aspect, the mapping relation establishing module further includes a preprocessing unit, configured to:

Correspondingly, the extraction unit is specifically configured to:

and acquiring a search keyword from the target search behavior log information, and acquiring the operation behaviors in a preset time interval after the user inputs the search keyword from the target operation behavior log information.

In a possible implementation manner of the second aspect, the mapping relation establishing module further includes a filtering unit, configured to:

correspondingly, the extraction unit is specifically configured to:

and taking the operation object corresponding to the effective operation behavior as an initial search object.

In a third aspect, an embodiment of the present application provides a terminal device, including: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the search method according to the first aspect as described above when executing the computer program.

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

In a fifth aspect, embodiments of the present application provide a computer program product for causing a terminal device to perform the search method of the first aspect described above when the computer program product is run on the terminal device.

It will be appreciated that the advantages of the second to fifth aspects may be found in the relevant description of the first aspect, and are not described here again.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments or the prior art will be briefly described below.

Fig. 1 is a block diagram of a terminal device provided in an embodiment of the present application;

fig. 2 is a schematic flow chart of a search method provided in the first embodiment of the present application;

fig. 3 is an application scenario diagram of a search method provided in an embodiment of the present application;

fig. 4 is another application scenario diagram of the search method provided in the embodiment of the present application;

fig. 5 is a further application scenario diagram of the search method provided in the embodiment of the present application;

FIG. 6 is a schematic diagram of an operating environment of a search method according to an embodiment of the present application;

fig. 7 is a flowchart of a method for establishing a mapping relationship list between a search object and a search keyword according to the first embodiment of the present application;

Fig. 8 is a flowchart of a method for establishing a mapping relationship list between a search object and a search keyword according to a second embodiment of the present application;

fig. 9 is a schematic structural diagram of a search device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".

In addition, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

The search method provided by the embodiment of the application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (augmented reality, AR)/Virtual Reality (VR) devices, notebook computers, ultra-mobile personal computer (UMPC), netbooks, personal digital assistants (personal digital assistant, PDA) and the like, and also can be applied to intelligent household appliances such as sound boxes, televisions, washing machines and the like, and the specific types of the terminal devices are not limited.

Taking the terminal equipment as a mobile phone as an example. Fig. 1 is a block diagram illustrating a part of a structure of a mobile phone according to an embodiment of the present application. Referring to fig. 1, a mobile phone includes: radio Frequency (RF) circuitry 110, memory 120, input unit 130, display unit 140, sensor 150, audio circuitry 160, wireless fidelity (wireless fidelity, wiFi) module 170, processor 180, and power supply 190. Those skilled in the art will appreciate that the handset configuration shown in fig. 1 is not limiting of the handset and may include more or fewer components than shown, or may combine certain components, or may be arranged in a different arrangement of components.

The following describes the components of the mobile phone in detail with reference to fig. 1:

the RF circuit 110 may be used for receiving and transmitting signals during the process of receiving and transmitting information or communication, specifically, after receiving downlink information of the base station, the downlink information is processed by the processor 180; in addition, the data of the design uplink is sent to the base station. Typically, RF circuitry includes, but is not limited to, antennas, at least one amplifier, transceivers, couplers, low noise amplifiers (Low Noise Amplifier, LNAs), diplexers, and the like. In addition, RF circuit 110 may also communicate with networks and other devices via wireless communications. The wireless communications may use any communication standard or protocol including, but not limited to, global system for mobile communications (Global System of Mobile communication, GSM), general packet radio service (General Packet Radio Service, GPRS), code division multiple access (Code Division Multiple Access, CDMA), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), long term evolution (Long Term Evolution, LTE)), email, short message service (Short Messaging Service, SMS), and the like. For example, the user inputs a contact to search at the interface of the call application, the terminal device recommends the contact to the user according to the keyword of the contact input by the user, and the user dials the phone of the contact to make a call through the RF circuit 110.

The memory 120 may be used to store software programs and modules, and the processor 180 performs various functional applications and data processing of the cellular phone by running the software programs and modules stored in the memory 120. The memory 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, memory 120 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The input unit 130 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the handset. In particular, the input unit 130 may include a touch panel 131 and other input devices 132. The touch panel 131, also referred to as a touch screen, may collect touch operations thereon or thereabout by a user (e.g., operations of the user on the touch panel 131 or thereabout by using any suitable object or accessory such as a finger, a stylus, etc.), and drive the corresponding connection device according to a predetermined program. Alternatively, the touch panel 131 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch azimuth of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device and converts it into touch point coordinates, which are then sent to the processor 180, and can receive commands from the processor 180 and execute them. In addition, the touch panel 131 may be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 130 may include other input devices 132 in addition to the touch panel 131. In particular, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, mouse, joystick, etc. For example, a user inputs a search keyword through an input interface to perform a search.

The display unit 140 may be used to display information input by a user or information provided to the user and various menus of the mobile phone. The display unit 140 may include a display panel 141, and alternatively, the display panel 141 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 131 may cover the display panel 141, and when the touch panel 131 detects a touch operation thereon or thereabout, the touch panel is transferred to the processor 180 to determine the type of the touch event, and then the processor 180 provides a corresponding visual output on the display panel 141 according to the type of the touch event. Although in fig. 1, the touch panel 131 and the display panel 141 are two independent components to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 131 and the display panel 141 may be integrated to implement the input and output functions of the mobile phone.

The handset may also include at least one sensor 150, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 141 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 141 and/or the backlight when the mobile phone moves to the ear. As one of the motion sensors, the accelerometer sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and direction when stationary, and can be used for applications of recognizing the gesture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that may also be configured with the handset are not described in detail herein.

Audio circuitry 160, speaker 161, microphone 162 may provide an audio interface between the user and the handset. The audio circuit 160 may transmit the received electrical signal converted from audio data to the speaker 161, and the electrical signal is converted into a sound signal by the speaker 161 to be output; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, which is received by the audio circuit 160 and converted into audio data, which is processed by the audio data output processor 180 and sent to, for example, another cell phone via the RF circuit 110, or which is output to the memory 120 for further processing. In this embodiment, the microphone 162 converts the collected sound signal into an electrical signal, and the electrical signal is received by the audio circuit 160 and then converted into audio data, and then the audio data is output to the processor 180, and the processor 180 performs a corresponding search according to the audio data.

WiFi belongs to a short-distance wireless transmission technology, and a mobile phone can help a user to send and receive emails, browse webpages, access streaming media and the like through the WiFi module 170, so that wireless broadband Internet access is provided for the user. Although fig. 1 shows a WiFi module 170, it is understood that it does not belong to the necessary constitution of the handset, and can be omitted entirely as required within the scope of not changing the essence of the invention.

The processor 180 is a control center of the mobile phone, connects various parts of the entire mobile phone using various interfaces and lines, and performs various functions and processes data of the mobile phone by running or executing software programs and/or modules stored in the memory 120 and calling data stored in the memory 120, thereby performing overall monitoring of the mobile phone. Optionally, the processor 180 may include one or more processing units; preferably, the processor 180 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 180.

The handset further includes a power supply 190 (e.g., a battery) for powering the various components, which may preferably be logically connected to the processor 180 via a power management system so as to provide for managing charging, discharging, and power consumption by the power management system.

Although not shown, the handset may also include a camera. Optionally, the position of the camera on the mobile phone may be front or rear, which is not limited in this embodiment of the present application. For example, the mobile phone scans the two-dimensional code through the camera, and performs corresponding search according to the scanned two-dimensional code.

Alternatively, the mobile phone may include a single camera, a dual camera, or a triple camera, which is not limited in the embodiments of the present application.

For example, a cell phone may include three cameras, one of which is a main camera, one of which is a wide angle camera, and one of which is a tele camera.

Alternatively, when the mobile phone includes a plurality of cameras, the plurality of cameras may be all front-mounted, all rear-mounted, or one part of front-mounted, another part of rear-mounted, which is not limited in the embodiments of the present application.

In addition, although not shown, the mobile phone may further include a bluetooth module, etc., which will not be described herein.

The search method provided in the embodiment of the present application is described below with reference to fig. 1. As shown in fig. 2, the search method provided in the embodiment of the present application includes:

s101: and obtaining a search keyword.

In an application scenario, when a user needs to search, a voice, an input character string or a scanned two-dimensional code is input in a search interface of a terminal device, and the terminal device extracts a search keyword from information input by the user.

In another application scenario, when the terminal device needs to recommend information for the user, such as recommending videos, products, services, etc., the user preference may be obtained according to the historical operation behavior of the user, such as shopping records, video viewing records, etc., and the search keyword may be obtained from the user preference.

Illustratively, as shown in fig. 3, in an application scenario, a user inputs "i want to get on the car" to search for an application program in an application program search interface, and the extracted search keyword is "get on the car". As shown in fig. 4, in another application scenario, a user inputs a voice "pay" through a voice assistant on a terminal device, the terminal device recognizes "pay" from the input voice and displays the "pay" in a search field of an application program, and a corresponding search keyword is "pay". As shown in fig. 5, in yet another application scenario, the user inputs "i want to see strong head" in the video search interface, and the search keyword extracted by the video application is "strong head".

S102: determining a target search object corresponding to a search keyword according to a pre-established mapping relation list of the search object and the search keyword; the mapping relation list of the search object and the search keyword is established according to historical search behaviors and operation behaviors after the historical search behaviors.

The search object may be an application, music, video, news, web page, or the like, among others. The mapping relation list of the search object and the search keyword can be established by the terminal equipment counting the historical search behavior of the current user and the operation behavior after the historical search behavior; or the server counts the historical searching behaviors of all users and the operation behaviors after the historical searching behaviors, and sends the built mapping relation list to the terminal equipment; the server can collect the historical searching behaviors of all users and the operation behaviors after the historical searching behaviors, send the historical searching behaviors and the operation behaviors to the terminal equipment, and the terminal equipment counts the historical searching behaviors and the operation behaviors to establish the historical searching behaviors and the operation behaviors.

For example, as shown in fig. 6, the terminal device 1 is communicatively connected to the server 2, where the server 2 may be a server, or a server cluster formed by several servers, or a cloud computing service center. The server counts the historical searching behaviors and operation behaviors of all terminal devices in communication connection with the server, and establishes a mapping relation list of the searching objects and the searching keywords. When acquiring the search keyword, the terminal device 1 acquires a mapping relationship list between the search object and the search keyword, which is sent by the server. In the mapping relationship list of the search objects and the search keywords, one search keyword may correspond to a plurality of search objects, and the terminal device may use all of the plurality of search objects corresponding to the search keywords as target search objects, or may use part of the search objects corresponding to the search keywords or one search object as target search objects.

S103: and displaying the target search object.

For example, as shown in fig. 3, in the mapping relationship list of the search object and the search keyword, the target search object corresponding to "get on the car" is "get on the car" fast dog get on the car "," high-land map "and" special state car ", and the terminal device displays the application program list according to the mapping relationship list of the search object and the search keyword. As shown in fig. 4, in the mapping relationship list of the search object and the search keyword, the target search object corresponding to "payment" is "payment treasures", "wallets", "WeChat" and "cloud flash payment", and the terminal device displays the application program list according to the mapping relationship list of the search object and the search keyword. As shown in fig. 5, in the mapping relationship list of the search object and the search keyword, the target search object corresponding to the "optical head strength" is "bear's on the show diary 2", "" bear's on the show diary "," "bear's on the show corpus", "bear's on the show space", and the terminal device displays the video list according to the mapping relationship list of the search object and the search keyword.

In the above embodiment, since the mapping relationship list of the search object and the search keyword is established according to the history search behavior and the operation behavior after the history search behavior, the search object may reflect the actual intention of the user after the search keyword is input. When a user inputs a search keyword, determining a target search object corresponding to the search keyword according to a mapping relation list of the search object and the search keyword, and recommending a more accurate search object for the user.

In the following, a method for establishing a mapping relationship list between a search object and a search keyword in the search method provided in the embodiment of the present application is described in detail.

As shown in fig. 7, the method for establishing a mapping relationship list between a search object and a search keyword according to the first embodiment of the present application includes:

s201: and acquiring search behavior log information and operation behavior log information of the user.

Specifically, stored in the search behavior log information is a user's historical search behavior, and the search behavior log information includes any one or more of a user ID, a search time, an original search string, a search exposure list, a search click list, and the like. The search exposure list stores: the terminal device recommends a search object for the user according to the extracted search keyword, for example, an application list recommended for the user according to the search keyword. The search click list stores: the user clicks the search object from the search exposure list, and when the user does not select the search object from the search exposure list, the record of the corresponding search click list is empty.

Stored in the operation behavior log information is a user's historical operation behavior, and the operation behavior log information includes one or more of a user ID, an operation behavior occurrence time, a name of a search object corresponding to the operation behavior, a category of the search object, a tag of the search object, and the like. Wherein the category of the search object and the tag of the search object are generated based on the characteristics of the search object. For example, when the search object is an application "WeChat", the category of the search object is chat, and the tag of the search object is social, communication, swipe, voice, and the like.

In one possible implementation, in order to improve the accuracy of the mapping relationship list, search behavior log information and operation behavior log information of all terminal devices connected to the server may be acquired.

For example, for a scenario in which a user searches for an application, a user inputs an original search string "i want to get on the vehicle" in an application search interface of a terminal device, and the recommended application on the terminal device is a driver version of a dog getting on the vehicle, and a dog getting on the vehicle (fast application), the recommended application on the terminal device forms a search exposure list, the user does not click on the application from the exposure list, and the corresponding click list is empty. The first record of table 1 is obtained by recording the time at which the search starts, searching for the corresponding user ID, searching for the exposure list, searching for the click list. In table 1, each search record of each user ID is recorded in turn, resulting in search behavior log information of the application program as shown in table 1.

TABLE 1

Correspondingly, the time of using the application program, the name of the application program, the category of the application program, the tag of the application program, and the like of each terminal device are recorded, and the behavior log information of using the application program shown in table 2 is obtained.

TABLE 2

S202: preprocessing the search behavior log information and the operation behavior log information to obtain target search behavior log information and target operation behavior log information.

Specifically, the obtained search behavior log information and operation behavior log information are subjected to data cleaning or feature engineering processing, including removing error data, repeated data, abnormal data and the like, so as to obtain target search behavior log information and target operation behavior log information. For example, data records with incomplete fields, records with contradictory temporal records, records with missing fields, etc. are removed.

S203: extracting a search keyword from target search behavior log information, acquiring an operation behavior in a preset time interval after a user inputs the search keyword from target operation behavior log information, and taking an operation object corresponding to the operation behavior as an initial search object.

Specifically, the search time is extracted from the target search behavior log information, and the search keyword is extracted from the original search string input by the user. For example, the keywords extracted from "i want to get on a car" are "get on a car", "help me order" are "order", "what news today" are "news", etc. And extracting the time of the operation behavior, the duration of the operation behavior and the name of the operation object from the target operation behavior log information. For example, for searching for the behavior of an application, the name of the application opened by the user and the time when the application starts to be used are extracted from the target operation behavior log information. According to the search time and the occurrence time of the operation behaviors, counting operation objects corresponding to the operation behaviors of the user after the original search character string is input each time, and taking the operation objects corresponding to all the operation behaviors in a preset time interval after the original search character string is input as initial search objects.

For example, for the operation behavior of the application program, the application program used in a preset time interval after the user inputs the original search string is counted, and the counted application program is used as the application program corresponding to the search keyword. For example, the time interval is set to be 30 seconds, the original search string input by a certain user is "i want to get a car", the search time is "2019062015:00:00", the extracted search keyword is "get a car", and then the application programs used in the time periods of "2019062015:00:00 to 20190620 15:00:30" on the terminal device are counted, and the application program in the time period is the initial search object.

In one possible implementation manner, in order to improve accuracy of the calculation result, statistics is performed on all terminal devices connected to the server, the initial search object corresponding to each search keyword, and the same initial search objects corresponding to the same search keywords of all users are combined, so that each search keyword corresponds to a plurality of initial search objects. For example, for the operation behavior of using an application, if the search keyword extracted from the original search string of the user is "driving", the application used by the user within 30 seconds after the search is recorded; and when the search keywords of all users are "driving", counting the application programs used within 30 seconds after searching, and merging the same application programs to obtain the counting result shown in the table 3.

TABLE 3 Table 3

Due to some common high-frequency operation behaviors, the high-frequency operation behaviors often appear in a search list, and the result is disturbed; there are also low frequency operation behaviors that use less frequently, and calculation errors are larger due to too little data volume. In one possible implementation manner, after the operation behaviors in the preset time interval after the user inputs the search keyword are obtained from the target operation behavior log information, deleting the high-frequency operation behaviors with the operation frequency being greater than the first threshold and deleting the low-frequency operation behaviors with the operation frequency being less than the second threshold to obtain effective operation behaviors, and taking the operation object corresponding to the effective operation behaviors as an initial search object, thereby improving the accuracy of calculation. Illustratively, in statistics of applications corresponding to the search keywords, high-frequency applications that are used more frequently by the user and low-frequency applications that are used less frequently are removed. For example, for the application program of the front 5 of the arrangement corresponding to "get on the car" in table 3, the application programs are "WeChat", "drop trip", "pay treasures", "Goldmap", "today's headlines", wherein "WeChat", "pay treasures", "today's headlines" belong to high frequency application programs, and when the high frequency operation behavior with higher operation frequency needs to be removed, the three application programs are removed from the application program list; when the low-frequency operation behavior with the lower operation frequency needs to be removed, for example, the application program with the use number < = 1000 times can be removed, i.e. the application program with the lower use frequency is removed from the list.

It will be appreciated that in another possible implementation, only one initial search object corresponding to each search keyword may be counted. For example, for an application search with a search keyword of "driving", only the application that is used first after the user inputs the original search string, or the application that is used the most after the user inputs the original search string, or the application that is used the longest after the user inputs the original search string may be counted.

S204: at least one behavior feature value of the initial search object is obtained.

In one possible implementation, the behavior feature value is obtained by counting initial search objects corresponding to search keywords of all users. The behavior feature value includes a number of times the initial search object is used, an average use time period of the initial search object, whether the initial search object is selected when displayed in the search exposure list, and/or a usage number of times the initial search object is used. For example, for the initial search object "the german map", the behavior feature value includes the number of times of using the "the german map", the average duration of using the "the german map", whether or not the "the german map" exists in the recommendation list when the search keyword is "the car is driven", whether or not the user clicks the "the german map", "the german map" from the recommendation list, and the like.

After merging initial search objects corresponding to the search keywords of all users, calculating average use duration of a certain initial search object according to operation duration of all users on the initial search object; counting the times of operating the initial search object by all users; and calculating the ratio of the number of people of the initial search object to the total number of people to obtain the usage frequency ratio of the initial search object, and merging all records to obtain the user behavior broad table. For example, as shown in table 4, in the search of the application program, the search keyword is "getting a car", the application programs used by all users within 30 seconds after the search are counted when the search keyword is "getting a car", and the "average time length", "the number of times of use", and the "number of times of use ratio" of the corresponding application programs are calculated, so as to obtain the application program broad table corresponding to the search keyword "getting a car".

TABLE 4 Table 4

S205: and calculating the confidence score of the initial search object according to the at least one behavior characteristic value and the preset weight coefficient corresponding to each behavior characteristic value.

Specifically, the product of each behavior characteristic value and the corresponding preset weight coefficient is summed to obtain the confidence score of the corresponding initial search object.

For example, assuming that the behavior feature value of the confidence score of the initial search object is calculated to include the number of times of use of the initial search object, the average use time length of the initial search object, and the use time ratio of the initial search object, the number of times of use of the initial search object, the average use time length of the initial search object, and the weight coefficient of the use time ratio of the initial search object corresponding to a certain search keyword are respectively 0.4, 0.3, and 0.3, normalizing each behavior feature value to obtain the use time number of the initial search object, the average use time length of the initial search object, and the use time ratio of the initial search object are respectively 0.5, and 0.1, and adding the product of the value corresponding to each behavior feature value and the weight coefficient, that is, 0.4×0.5+0.3×0.5+0.3×0.1=0.38, to obtain the confidence score.

For another example, in one application scenario, the behavior feature value for calculating the confidence score includes a usage frequency of the initial search object, and the confidence score is calculated according to the usage frequency of the initial search object, for example, in table 5, in statistics of usage records of the application program, after the user searches for "getting a car", 53% of people use "drop out" and the usage frequency of "drop out" corresponding to "getting a car" is 0.53, and the confidence of "drop out" corresponding to "getting a car" is 0.53. Similarly, if the usage frequency of the "Goldmap" corresponding to the "taxi" is calculated to be 0.25, the confidence of the "Goldmap" corresponding to the "taxi" is calculated to be 0.25, and the confidence score of each application program corresponding to each search keyword is obtained.

TABLE 5

S206: and establishing a mapping relation list of the search object and the search keywords according to the confidence score of the initial search object.

In one possible implementation, the confidence score of the initial search object is converted into a confidence score of the search keyword, and the confidence score of the search keyword which is larger than the preset confidence threshold is used as the weight value of the search keyword. For example, if the confidence score of the initial search object "pay treasures" corresponding to the search keyword "pay" is 0.35, the confidence score of "pay" in the search keywords corresponding to "pay treasures" is 0.35, and besides, "order", "take out" and the like are also included in the search keywords corresponding to "pay treasures". And sequentially converting the confidence scores of the initial search objects corresponding to the search keywords into the confidence scores of the search keywords corresponding to the initial search objects. And for each initial search object, carrying out descending order arrangement on the search keywords according to the corresponding confidence scores, taking the confidence score in the records with the confidence score larger than the preset confidence threshold value as a weight value, wherein each weight value corresponds to one record, and obtaining a mapping relation list of the search objects and the search keywords. That is, in the mapping relation list of the search objects and the search keywords, each initial search object corresponds to a plurality of search keywords, and each search keyword corresponds to a weight value. For example, for searching an application program, the confidence score of the application program in table 5 is converted into the confidence score of the search keyword, after the confidence scores are arranged in descending order, the confidence score in the record of the first 5 is the weight value of the search keyword, wherein the plurality of search keywords corresponding to the "drop trip" and the corresponding weight value are respectively ("drop", 0.9), ("trip", 0.56), ("get a car", 0.53), ("drive by generation", 0.45), ("take out", 0.25), and the search keyword is the intention label. And counting the weight value of each search keyword corresponding to each application program to obtain a mapping relation list of the application programs and the search keywords shown in the table 6.

TABLE 6

When the user searches next time, extracting a search keyword from the original search character string, and recommending the search object corresponding to the record with the weight value of the search keyword larger than the preset weight threshold to the user as a target search object according to the mapping relation list of the search object and the search keyword. For example, when a user inputs a "driving" search application, the applications corresponding to the "driving" are ranked according to the weight value, and the applications corresponding to the first 5 ranked records are recommended to the user.

In the above embodiment, by acquiring the search behavior log information and the operation behavior log information of the user, extracting the operation behavior in the preset time interval after the search keyword is input from the log information, using the operation object corresponding to the operation behavior as the initial search object, and calculating the confidence score of the initial search object according to at least one behavior feature value of the initial search object and the preset weight coefficient corresponding to each behavior feature value. Since the behavior feature value represents feature information of the initial search object, the confidence score calculated from the behavior feature value represents the intention of the user to operate the initial search object. According to the confidence score of the initial search object, a mapping relation list of the search object and the search keywords is established, the real search intention of the user can be accurately reflected, and when the user searches, more accurate services can be recommended for the user according to the mapping relation list of the search object and the search keywords.

As shown in fig. 8, the search method provided in the second embodiment of the present application includes:

s301: and acquiring search behavior log information and operation behavior log information of the user.

S302: preprocessing the search behavior log information and the operation behavior log information to obtain target search behavior log information and target operation behavior log information.

S303: extracting a search keyword from target search behavior log information, acquiring an operation behavior in a preset time interval after a user inputs the search keyword from target operation behavior log information, and taking an operation object corresponding to the operation behavior as an initial search object.

Wherein, S301-S303 are the same as S201-S203, and are not described herein.

S304: and calculating the confidence score of the initial search object according to the search keyword, the initial search object and a preset prediction model.

The preset prediction model is obtained by training a learning model by using a search keyword, an initial search object corresponding to the search keyword and a confidence score as training samples and adopting a machine learning or deep learning algorithm. Specifically, a search keyword and an initial search object corresponding to the search keyword are input into a learning model, characteristics of the search keyword, characteristics of the initial search object and characteristics of operation behaviors corresponding to the search keyword are extracted, corresponding confidence scores are output, parameters of the learning model are optimized according to the output confidence scores and differences of the confidence scores in training samples, optimal parameters of the learning model are obtained, and a preset prediction model is generated according to the optimal parameters. The features of the search keywords are any one or more of the hotness of the keywords, the total search times, the search times ratio, word2vec word vectors corresponding to the search keywords, the features of similar keywords of the search keywords and the like. The features of the initial search object include any one or more of the name, category, tag of the search object, corresponding word2vec word vector, features of similar search objects of the search object, and the like. The operation behavior is characterized by any one or more of average use time length, use heat, total use times, use times ratio and the like of the initial search object after the search.

In one possible implementation manner, the learning model may be a machine learning model such as logistic regression, gradient lifting tree, random forest, etc., or a deep learning model such as convolutional neural network model (Convolutional Neural Network, CNN), fully connected neural network model (Fully Connected Neural Network, FCNN), etc., and the method for training the learning model may be a supervised learning algorithm or a semi-supervised learning algorithm. The learning model is trained by a semi-supervised classification algorithm, and a confidence score of each initial search object corresponding to each search keyword is set according to each search keyword corresponding to the initial search object for a first preset number of initial search objects. For example, the number of applications to be calculated with confidence scores is 1000, and 100 applications are selected, wherein the confidence of the "drop travel" corresponding to the "getting on the car" is set to be 0.5, the confidence of the "God map" corresponding to the "getting on the car" is set to be 0.3, the confidence of the "pay" corresponding to the "pay treasures" is set to be 0.4, and the confidence of the "WeChat" corresponding to the "pay" is set to be 0.4, so that the confidence scores of the 100 applications and the corresponding search keywords are sequentially set. And training and learning the learning model by taking the set first preset number of initial search objects, search keywords and confidence scores as training samples to obtain a first candidate model. And generating corresponding training samples according to the second preset number of initial search objects, and performing 'relearning' on the first candidate model to optimize parameters of the first candidate model and correct inaccurate confidence scores. For example, after a first candidate model is trained by selecting 100 application programs from 1000 application programs with confidence scores to be calculated, inputting the remaining 900 application programs into the first candidate model, selecting 100 application programs with highest confidence degrees according to the confidence scores corresponding to each application program, and generating training samples again according to the 100 application programs with highest confidence degrees and the 100 application programs for training the first candidate model, wherein the training samples are used for carrying out 'relearning' on the first candidate model so as to optimize parameters of the first candidate model, and obtaining a second candidate model. And sequentially iterating and calculating by adopting the method to obtain a prediction model. The selection method of the application program with highest reliability can be selected according to the difference between the output results of the multiple learning models. For example, the number of the first candidate models is 3, the remaining 900 application programs are respectively input into the 3 first candidate models, and the application program corresponding to the confidence score with the smallest difference between the output results of the 3 first candidate models is selected as the application program with the highest credibility. And inputting the search keywords and the initial search object into a prediction model, and calculating the confidence score of the initial search object.

S305: and establishing a mapping relation list of the search object and the search keywords according to the confidence score of the initial search object.

The S305 is the same as S206, and will not be described herein.

In the above embodiment, by acquiring the search behavior log information and the operation behavior log information of the user, extracting the operation behavior in the preset time interval after the search keyword is input from the log information, taking the operation object corresponding to the operation behavior as the initial search object, and calculating the confidence score of the initial search object according to the search keyword, the initial search object and the preset prediction model.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.

Corresponding to the searching method described in the above embodiments, fig. 9 shows a block diagram of the searching apparatus provided in the embodiment of the present application, and for convenience of explanation, only the portion relevant to the embodiment of the present application is shown.

Referring to fig. 9, the search apparatus includes:

an acquisition module 10 for acquiring a search keyword;

the determining module 20 is configured to determine a target search object corresponding to a search keyword according to a pre-established mapping relationship list between the search object and the search keyword; the mapping relation list of the search object and the search keyword is established according to historical search behaviors and operation behaviors after the historical search behaviors;

and a display module 30, configured to display the target search object.

In one possible implementation manner, the searching device further includes a mapping relationship establishing module, where the mapping relationship establishing module includes:

In one possible implementation, the computing unit is specifically configured to:

In one possible implementation, the behavior feature value includes a number of uses of the initial search object, an average duration of use of the initial search object, and/or a usage number of times of the initial search object.

In a possible implementation manner, the establishing unit is specifically configured to:

In a possible implementation, the establishing unit is further configured to:

In one possible implementation manner, the determining module is specifically configured to:

In one possible implementation manner, the mapping relationship establishing module further includes a preprocessing unit, configured to:

correspondingly, the extraction unit is specifically configured to:

In a possible implementation manner, the mapping relationship establishing module further includes a filtering unit, configured to:

correspondingly, the extraction unit is specifically configured to:

It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein again.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other manners. For example, the apparatus/terminal device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each method embodiment described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.

The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. A search method, comprising:

acquiring search keywords;

determining a target search object corresponding to a search keyword according to a pre-established mapping relation list of the search object and the search keyword; the mapping relation list of the search object and the search keyword is established according to historical search behaviors and operation behaviors after the historical search behaviors; displaying the target search object;

the mapping relation list of the search object and the search keyword is established in the following way:

acquiring search behavior log information and operation behavior log information of a user;

Acquiring a search keyword from the search behavior log information, acquiring an operation behavior in a preset time interval after a user inputs the search keyword from the operation behavior log information, and taking an operation object corresponding to the operation behavior as an initial search object;

calculating a confidence score of the initial search object;

2. The search method of claim 1, wherein said calculating a confidence score for the initial search object comprises:

3. The search method of claim 2, wherein the behavior feature value includes a number of times an initial search object is used, an average duration of use of the initial search object, and/or a usage number of times the initial search object is used.

4. The search method of claim 1, wherein said calculating a confidence score for the initial search object comprises:

5. The search method of claim 1, wherein the calculating the weight value of the search keyword according to the confidence score of the initial search object comprises:

6. The method of claim 5, wherein determining the target search object corresponding to the search keyword comprises:

7. The search method of claim 1, further comprising, prior to said obtaining search keywords from said search behavior log information:

8. The search method according to any one of claims 1 to 7, characterized by further comprising, after the operation behavior within a preset time interval after the user inputs the search keyword is acquired from the operation behavior log information:

9. A search apparatus, comprising:

the acquisition module is used for acquiring the search keywords;

the display module is used for displaying the target search object;

the searching device further comprises a mapping relation establishing module, wherein the mapping relation establishing module comprises:

the establishing unit is used for calculating the weight value of the search keyword according to the confidence score of the initial search object; and establishing a mapping relation list of the search object and the search keywords according to the weight values of the search keywords.

10. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 8 when executing the computer program.

11. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the method according to any one of claims 1 to 8.