CN114328842A

CN114328842A - Information recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN114328842A
Application number: CN202111680401.2A
Authority: CN
Inventors: 马晶义; 宋丹丹; 张玉东; 张铮; 侯秀霞; 王欢
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-12-30
Filing date: 2021-12-30
Publication date: 2022-04-12

Abstract

The disclosure provides an information recommendation method, relates to the field of artificial intelligence, and particularly relates to intelligent search, big data and natural language processing technologies. The specific implementation scheme is as follows: extracting query keywords from the received query statement; determining target object data items associated with the query keywords in the object data set according to the query keywords; obtaining a target object according to the target object data item; and recommending a query statement to the target object. The disclosure also provides an information recommendation device, an electronic device and a storage medium.

Description

Information recommendation method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to intelligent search, big data, and natural language processing techniques. More specifically, the present disclosure provides an information recommendation method, apparatus, electronic device, and storage medium.

Background

On the intelligent question-and-answer platform, a user (e.g., a question master) may issue a question to query the answer to the question. Other users (e.g., the answering owner) may also answer the issued question. The relevant platform operators may recruit professionals as answers master.

Disclosure of Invention

The disclosure provides an information recommendation method, an information recommendation device, information recommendation equipment and a storage medium.

According to a first aspect, there is provided an information recommendation method, the method comprising: extracting query keywords from the received query statement; according to the query key words, determining target object data items related to the query key words in an object data set; obtaining a target object according to the target object data item; and recommending the query statement to the target object so that the target object responds according to the query statement.

According to a second aspect, there is provided an information recommendation apparatus comprising: the extraction module is used for extracting query keywords from the received query sentences; a first determining module, configured to determine, according to the query keyword, a target object data item associated with the query keyword in an object data set; an obtaining module, configured to obtain a target object according to the target object data item; and the recommending module is used for recommending the query statement to the target object so that the target object can respond according to the query statement.

According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method provided in accordance with the present disclosure.

According to a fourth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method provided in accordance with the present disclosure.

According to a fifth aspect, a computer program product is provided, comprising a computer program which, when executed by a processor, implements a method provided according to the present disclosure.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of an exemplary system architecture to which information recommendation methods and apparatus may be applied, according to one embodiment of the present disclosure;

FIG. 2 is a flow diagram of an information recommendation method according to one embodiment of the present disclosure;

FIG. 3A is a schematic diagram of an object data set, according to one embodiment of the present disclosure;

FIG. 3B is a schematic diagram of an object data set, according to another embodiment of the present disclosure;

FIG. 3C is a schematic diagram of an object data set, according to another embodiment of the present disclosure;

FIG. 4 is a flow diagram of an information recommendation method according to another embodiment of the present disclosure;

FIG. 5 is a flow diagram of an information recommendation method according to another embodiment of the present disclosure;

FIG. 6 is a schematic diagram of an object data item, according to one embodiment of the present disclosure;

FIG. 7 is a block diagram of an information recommendation device according to one embodiment of the present disclosure; and

fig. 8 is a block diagram of an electronic device to which an information recommendation method may be applied according to one embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

On the intelligent question-answering platform, a user (a question master) can issue a question to inquire about the answer of the question. The user (the answering machine) can also answer the issued question. The platform operator may recruit operation and maintenance personnel as the answer master. The platform operator may also push questions to multiple users to have the questions answered.

On the intelligent question-answering platform, the questions are various and the related fields are different. Only some users tend to answer questions. This results in many questions not being answered effectively.

And (4) carrying out statistical analysis on the problems on the platform to obtain a distribution rule curve of the problems. The distribution law curve is similar to a normal distribution curve. Most of the problems are concentrated on the convex head part in the middle of the curve, and a small part of personalized and scattered problems are distributed on the tail parts at two ends of the curve. The problem at the head may be referred to as a conventional problem. These Tail-in problems may be referred to as The Long Tail (The Long Tail) problem.

Few or no answers were made to the long-tailed question. When the total number of users is large, the proportion of the topics issuing the long-tail questions to all users is low, but the total number of the topics is still large. For example, 10 hundred million users are all, and the total number of topics issuing a certain question is 0.1% of the total number of users. This problem may be referred to as the long tail problem. And the topic that issued the question was 1 million. It can be seen that it is necessary to answer the long-tailed question.

The platform operator can use the search engine to solve partial long-tail problems. However, content resources related to the long-tailed question are very scarce, and it is difficult to grasp a proper answer through a network. The platform operator may also hire a professional answering machine to answer the long-tailed question. However, the total amount of the long-tail questions is not low, and a large amount of human resources are consumed for solving each long-tail question. Moreover, a long-tail question is solved by an answering owner with a certain time cost, a platform operator also needs to examine and verify the answer, the process is long, and the timeliness is difficult to meet.

Fig. 1 is a schematic diagram of an exemplary system architecture to which the information recommendation method and apparatus may be applied, according to one embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the information recommendation method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the information recommendation device provided by the embodiment of the present disclosure may be generally disposed in the server 105. The information recommendation method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the information recommendation device provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105.

Fig. 2 is a flowchart of an information recommendation method according to one embodiment of the present disclosure.

As shown in fig. 2, the method 200 may include operations S210 to S240.

In operation S210, a query keyword is extracted from the received query sentence.

In the disclosed embodiments, the query statement may be an object input question.

For example, the query statement may be "is an elderly person over 90 years old yet to be handed in AA cooperative medical insurance? ".

In the embodiment of the disclosure, the query keyword can be extracted based on a deep learning technology.

For example, query terms may be extracted using a trained LSTM (Long and Short Term Memory) model. For example, the query keyword may be extracted using a trained BERT (transform from transform) model and CNN (Convolutional Neural Network) model.

For example, from the query statement described above, the extracted query keyword may be "cooperative medical insurance".

In operation S220, a target object data item associated with the query keyword is determined in the object data set according to the query keyword.

In the disclosed embodiment, the object data set may be derived from historical query statements.

For example, the object data set may be derived from log data associated with the query statement.

For example, it may be determined whether there is data in the object data set that is completely consistent with the query keyword to determine the target object data item. In one example, the object data set may be a data table. The object data item may be a row of data in the data table. If the data table has search keywords completely consistent with the 'cooperative medical insurance'. If the identifier of the search keyword is Query _1, the line where the search keyword Query _1 is located may be used as the target object data item.

In operation S230, a target object is obtained according to the target object data item.

For example, when an information Query is performed, the object User _1 has once input a search keyword Query _ 1. As described above, the object data set is derived from log data. Therefore, one object data item of the object data set may include a search keyword Query _1 and an object User _ 1. After determining that the object data item L _1 is a target object data item, an object User _1 in the object data item L _1 may be a target object.

In operation S240, a query statement is recommended to the target object so that the target object responds according to the query statement.

For example, "do the elderly over 90 years old also meet AA cooperative medical insurance? "recommended to the subject User _1 so that the subject User _1 responds.

It should be noted that the query statement may be the long tail problem described above, or may be the conventional problem described above, which is not limited by the present disclosure.

Through the embodiment of the disclosure, the potential users who can answer the long tail can be determined according to the query key words.

In some embodiments, an object data set may include a plurality of object data items, including the following entries: a search keyword, an object identification associated with the search keyword, and a time attribute.

In some embodiments, the object data items may also include the following entries: the search keyword identification, the number of times the search keyword is searched within a predetermined period of time, and the number of objects associated with the search keyword within the predetermined period of time.

FIG. 3A is a schematic diagram of an object data set, according to one embodiment of the present disclosure.

As shown in fig. 3A, a plurality of object data items may be included in object data set 310, such as object data item L _1, object data item L _2, object data item L _3, object data item L _4, and object data item L _ N.

In this embodiment, the object data item includes the following items: a search keyword Query, an object identification User _ ls associated with the search keyword, and a time attribute DT. For example, in the object data item L _1, the value of the search keyword is "cooperative medical insurance", the value of the object identifier is "User _ 1", and the value of the time attribute is "1 × 21 months".

It is understood that "BB" in the search keyword "BB install process" in the object data item L _2 is an application program. The "CC" in the search keyword "CC installation process" in the object data item L _ N is another application.

FIG. 3B is a schematic diagram of an object data set, according to another embodiment of the present disclosure.

As shown in fig. 3B, the difference from the object data set 310 is that the object data items in the object data set 320 further include the following entries: the search keyword identifies Query _ ID, the number of times the search keyword is searched for within a predetermined period of time Query _ num, and the number of objects associated with the search keyword within the predetermined period of time User _ num.

For example, in the object data item L _1, the value of the search keyword identification is "Query _ 1", the value of the number of times the search keyword is searched for within a predetermined period is "21", and the value of the number of objects associated with the search keyword within the predetermined period is "1".

FIG. 3C is a schematic diagram of an object data set, according to another embodiment of the present disclosure.

As shown in fig. 3C, the difference from the object data set 320 is that the object data items in the object data set 320 further include the following entries: question.

For example, in the object data item L _1, the value of the question is "does the elderly aged 70 or older still meet AA cooperative medical insurance". In one example, the value of the question entry is the query statement above.

In some embodiments, the object data set is created from a search log over a predetermined period of time. For example, the search logs may be logs of various search engines. For example, the predetermined period may be, for example, 10 natural months before "1 × 21 days" shown in fig. 3A.

In some embodiments, determining, from the query keyword, a target object data item in the object data set associated with the query keyword comprises: at least one target object data item is determined in the object data set, the search keyword of the at least one target object data item matching the query keyword.

For example, the query keyword QK _1 is "cooperative medical insurance" as an example. Based on various matching techniques, it may be determined that the search keyword "collaborative medical insurance" in FIG. 3A, for example, matches the query keyword QK _ 1. It is possible to determine, for example, the object data item L _1 in fig. 3A as one target object data item.

For another example, the query keyword QK _2 is "installation process". Based on various matching techniques, it can be determined that, for example, the search keywords "BB installation process" and "CC installation process" in fig. 3A both match the query keyword QK _ 2. It may be determined that, for example, the object data item L _2 and the object phase data item L _ N in fig. 3A are both target object data items.

Fig. 4 is a flowchart of an information recommendation method according to another embodiment of the present disclosure.

As shown in fig. 4, the method 400 may include operations S410, S421 to S425, S430, S440, and S450.

In operation S410, a query keyword is extracted from the received query sentence.

For example, in 1 × month 22 days × hour × minute, the received query statement may be "during the installation of BB, the license server state is not running, and cannot be started all the time, and it is unknown what reason it is". Based on this, the extracted query keyword QK _3 may be "the installation process of BB".

In operation S421, it is determined whether the search keyword of the object data item matches the query keyword.

In the embodiment of the present disclosure, in response to the search keyword of the plurality of object data items matching the query keyword, operation S422 may be performed.

In the embodiment of the present disclosure, in response to the search keyword of any one of the object data items not matching the query keyword, operation S450 may be performed. In operation S450, the flow ends.

For example, it may be determined whether a search keyword in the object data item matches a query keyword using an ES (elastic search) technique. The ES technology is an intra-site full-text search technology. The ES technology can be realized based on an open-source full-text search engine Lucene. The ES technology adopts Lucene as an index and search core, and can support clustering and distribution natively. The ES technology may not support the database table-linked query function, and may be used as an aid to searching. The raw data is still stored in the database. For example, in the search process, the query keyword QK _3 is first segmented, each segmented word is used as a matching condition, and the sum of the matching degrees of all the segmented words is obtained as the matching degree value of one search keyword. Next, a plurality of search keywords having a matching degree value with the query keyword QK _3 greater than a preset matching degree threshold may be determined. Candidate object data items may be quickly determined to conserve computing resources.

For example, based on the ES technique described above, it can be determined that, for example, the search keyword "BB installation process" of the object data item L _2, the search keyword "BB installation process" of the object data item L _3, the search keyword "BB installation" of the object data item L _4, and the search keyword "CC installation process" of the object data item L _ N in fig. 3A match the installation process "of the query keyword QK _ 3" BB described above.

In operation S422, a plurality of candidate object data items are determined in the object data set.

For example, the object data item L _2, the object data item L _3, the object data item L _4, and the object data item L _ N may be taken as candidate data items.

In operation S423, similarities between the search keywords of the candidate object data items and the query keyword, respectively, are determined, resulting in a plurality of similarities.

For example, the similarity between the search keywords of the plurality of candidate object data items and the query keyword, respectively, may be calculated using a BERT model. In one example, the similarity computed by the BERT model may be a semantic similarity between keywords. Search keywords closer to the semantics of the query sentence can be accurately determined from the candidate object data items so as to accurately find an answer master that is likely to solve the long-tail question.

In operation S424, it is determined whether the similarity is greater than or equal to a preset similarity threshold?

In the embodiment of the present disclosure, in response to the similarity being greater than or equal to the preset similarity threshold, operation S425 may be performed.

In the embodiment of the present disclosure, in response to the similarity being less than the preset similarity threshold, the operation S450 described above may be performed.

For example, it may be determined that: for example, the search keyword "BB installation process" of the object data item L _2, the search keyword "BB installation process" of the object data item L _3, and the search keyword "BB installation" of the object data item L _4 in fig. 3A respectively have a similarity to the query keyword QK _3 described above greater than a preset similarity threshold. And the similarity between the search keyword "CC installation process" of the object data item L _ N and the query keyword QK _3 in fig. 3A, for example, is less than a preset similarity threshold.

In operation S425, at least one target object data item is determined from the plurality of candidate object data items according to the plurality of similarities and the time attributes of the corresponding candidate object data items.

In the disclosed embodiment, a target candidate object data item is determined from a plurality of candidate object data items according to a plurality of similarities.

For example, for the object data item L _2, the object data item L _3, and the object data item L _4 in fig. 3A, for example, the similarity between the search keyword and the query keyword QK _3 of the three is greater than the preset similarity threshold. The object data item L _2, the object data item L _3, and the object data item L _4 may be determined as target candidate object data items.

In the embodiment of the present disclosure, according to the object identifier and the time attribute of the target candidate object data item, the deduplication is performed on the target candidate object data item, so as to obtain at least one target object data item.

For example, the object of the object data item L _2 is identified as "User _ 2", the object of the object data item L _3 is identified as "User _ 2", and the object of the object data item L _4 is identified as "User _ 3".

The time attribute DT of the object data item L _2 is "1 × month 21 day", the time attribute DT of the object data item L _3 is "1 × month 19 day", and the time attribute DT of the object data item L _4 is "1 × month 20 day".

The object identifications of the object data item L _2 and the object data item L _3 are the same, and the time corresponding to the time attribute of the object data item L _2 is closer to the time when the query statement is received. And performing duplicate removal on the three target object data items to obtain at least one target object data item which is an object data item L _2 and an object data item L _ 4. And the duplication removal is carried out based on the time attribute, so that the method is favorable for finding out the answer owner for solving the long-tail problem.

In operation S430, a target object is obtained according to at least one target object data item.

For example, in the case where the object data item L _2 and the object data item L _4 are target object data items, the target objects are User _2 and User _ 3.

In operation S440, a query statement is recommended to the target object so that the target object responds according to the query statement.

For example, during the installation process of the query statement "BB" may be recommended to the target object User _2 and the target object User _3, the state of the license server is not running, and cannot be started all the time, and no reason is known, so that the objects User _2 and User _3 respond according to the query statement.

In some embodiments, the method 400 is different from the method 400 in that, in operation S423, similarities between the search keywords of the plurality of candidate object data items and the query keywords respectively may be calculated by using an LSTM model or an ERNIE (Enhanced retrieval through Knowledge Integration Enhanced Representation) model.

Fig. 5 is a flowchart of an information recommendation method according to another embodiment of the present disclosure.

As shown in fig. 5, the method 500 may be performed prior to operation S210 of the method 200. The method 500 may include operations S501 and S502.

In operation S501, a plurality of consistent object data items in the object data set, for which search keywords are consistent, are determined.

For example, it may be determined that the semantics of the search keywords "BB installation process", "process of installation of BB", and "BB installation" in the object data set 310 are consistent, and further, it may be determined that the object data item L _2, the object data item L _3, and the object data item L _4 are three consistent object data items.

In operation S502, a plurality of consistent object data items are merged into one object data item.

In an embodiment of the present disclosure, one object data item includes the following items: a search keyword, a list of object identifications associated with the search keyword, and a list of time attributes.

For example, the search keyword of any one of the object data of the three uniform object data items described above may be used as the search keyword of one object data item. In one example, the "BB installation process" may be used as a search keyword for one object data item.

The object identification list associated with the search keyword comprises User _2, User _2 and User _ 3.

The time attribute list includes "1 × month 21 day", "1 × month 19 mesh", and "1 × month 20 day".

FIG. 6 is a schematic diagram of an object data item, according to one embodiment of the present disclosure.

As shown in fig. 6, one object data item L _ merge includes the search keyword "BB installation process". The object identification list in one object data item L _ merge contains User _2, and User _ 3. The time attribute list of one object data item L _ merge contains "1 × month 21 day", "1 × month 19 day", and "1 × month 20 day". An object data item L _ merge may be merged according to, for example, method 500 of fig. 5.

Fig. 7 is a block diagram of an information recommendation device according to one embodiment of the present disclosure.

As shown in fig. 7, the apparatus 700 may include an extraction module 710, a first determination module 720, an obtaining module 730, and a recommendation module 740.

The extracting module 710 is configured to extract a query keyword from the received query statement.

The first determining module 720 is configured to determine, according to the query keyword, a target object data item associated with the query keyword in an object data set.

An obtaining module 730, configured to obtain the target object according to the target object data item.

And a recommending module 740, configured to recommend the query statement to the target object, so that the target object responds according to the query statement.

In some embodiments, the object data set includes a plurality of object data items, the object data items including the following entries: the search keyword, an object identifier associated with the search keyword, and a time attribute.

In some embodiments, the object data item further includes the following items: the search keyword identification, the number of times the search keyword is searched within a predetermined period of time, and the number of objects associated with the search keyword within the predetermined period of time.

In some embodiments, the set of object data is created from a search log over a predetermined period of time.

In some embodiments, the first determining module comprises: the first determining sub-module is used for determining at least one target object data item in the object data set, and the search keyword of the at least one target object data item is matched with the query keyword.

In some embodiments, the obtaining module comprises: a second determining sub-module, configured to determine, according to the query keyword, a plurality of candidate object data items in an object data set, where search keywords of the plurality of candidate object data items are all matched with the query keyword; a third determining sub-module, configured to determine similarities between the search keywords of the multiple candidate object data items and the query keyword, respectively, so as to obtain multiple similarities; a fourth determining sub-module, configured to determine the at least one target object data item from the plurality of candidate object data items according to the plurality of similarities and time attributes of corresponding candidate object data items; and an obtaining submodule for obtaining the target object according to the at least one target object data item.

In some embodiments, the fourth determining sub-module includes: determining a target candidate object data item from the candidate object data items according to the plurality of similarities; and executing deduplication on the target candidate object data item according to the object identifier and the time attribute of the target candidate object data item to obtain the at least one target object data item.

In some embodiments, the apparatus 700 further comprises: a second determining module, configured to determine multiple consistent object data items consistent with the search keyword in the object data set; a merging module for merging a plurality of consistent object data items into one object data item, the one object data item including the following entries: the system comprises a search keyword, an object identification list and a time attribute list, wherein the object identification list is associated with the search keyword.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 8 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 8, the apparatus 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

A number of components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Computing unit 801 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 801 executes the respective methods and processes described above, such as the information recommendation method. For example, in some embodiments, the information recommendation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto device 800 via ROM 802 and/or communications unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the information recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the information recommendation method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. An information recommendation method, comprising:

extracting query keywords from the received query statement;

determining a target object data item associated with the query keyword in an object data set according to the query keyword;

obtaining a target object according to the target object data item; and

and recommending the query statement to the target object so that the target object responds according to the query statement.

2. The method of claim 1, wherein the object data set includes a plurality of object data items, the object data items including the following entries: a search keyword, an object identification associated with the search keyword, and a time attribute.

3. The method of claim 2, wherein the object data item further comprises the following items: a search keyword identification, a number of times the search keyword is searched for within a predetermined period of time, and a number of objects associated with the search keyword within the predetermined period of time.

4. The method of claim 2 or 3, wherein the object data set is created from a search log over a predetermined period of time.

5. The method of claim 2, wherein determining, from the query keyword, a target object data item in an object data set associated with the query keyword comprises:

determining at least one target object data item in the object data set, the search keyword of the at least one target object data item matching the query keyword.

6. The method according to claim 2 or 5, wherein said deriving a target object from said target object data item comprises:

determining a plurality of candidate object data items in an object data set according to the query keyword, wherein the search keyword of the candidate object data items is matched with the query keyword;

determining the similarity between the search keywords of the candidate object data items and the query keyword respectively to obtain a plurality of similarities;

determining the at least one target object data item from the plurality of candidate object data items according to the plurality of similarities and the time attributes of the corresponding candidate object data items; and

and obtaining the target object according to the at least one target object data item.

7. The method of claim 6, wherein said determining the at least one target object data item from the plurality of candidate object data items in dependence on the plurality of similarities and the temporal attributes of the corresponding candidate object data items comprises:

determining a target candidate object data item from a plurality of candidate object data items according to the plurality of similarities; and

and according to the object identification and the time attribute of the target candidate object data item, performing deduplication on the target candidate object data item to obtain the at least one target object data item.

8. The method of claim 1, further comprising:

determining a plurality of consistent object data items consistent with the search keyword in the object data set;

merging a plurality of consistent object data items into one object data item, the one object data item including the following entries: the system comprises a search keyword, an object identification list and a time attribute list, wherein the object identification list is associated with the search keyword.

9. An information recommendation apparatus comprising:

the extraction module is used for extracting query keywords from the received query sentences;

a first determining module, configured to determine, according to the query keyword, a target object data item associated with the query keyword in an object data set;

the obtaining module is used for obtaining a target object according to the target object data item; and

and the recommending module is used for recommending the query statement to the target object so that the target object can respond according to the query statement.

10. The apparatus of claim 9, wherein the object data set comprises a plurality of object data items, the object data items comprising the following entries: a search keyword, an object identification associated with the search keyword, and a time attribute.

11. The apparatus of claim 10, wherein the object data item further comprises the following items: a search keyword identification, a number of times the search keyword is searched for within a predetermined period of time, and a number of objects associated with the search keyword within the predetermined period of time.

12. The apparatus of claim 10 or 11, wherein the object data set is created from a search log over a predetermined period of time.

13. The apparatus of claim 10, wherein the first determining means comprises:

a first determining sub-module for determining at least one target object data item in the object data set, a search keyword of the at least one target object data item matching the query keyword.

14. The apparatus of claim 10 or 13, wherein the obtaining means comprises:

a second determining sub-module, configured to determine, according to the query keyword, a plurality of candidate object data items in an object data set, where search keywords of the plurality of candidate object data items are all matched with the query keyword;

a third determining submodule, configured to determine similarities between the search keywords of the multiple candidate object data items and the query keyword, respectively, so as to obtain multiple similarities;

a fourth determining sub-module, configured to determine the at least one target object data item from the plurality of candidate object data items according to the plurality of similarities and time attributes of corresponding candidate object data items; and

and the obtaining submodule is used for obtaining the target object according to the at least one target object data item.

15. The apparatus of claim 14, wherein the fourth determination submodule comprises:

16. The apparatus of claim 9, further comprising:

a second determining module, configured to determine multiple consistent object data items consistent with the search keyword in the object data set;

a merging module for merging a plurality of consistent object data items into one object data item, the one object data item including the following entries: the system comprises a search keyword, an object identification list and a time attribute list, wherein the object identification list is associated with the search keyword.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1 to 8.

19. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 8.