CN114003625A

CN114003625A - Information searching method and device

Info

Publication number: CN114003625A
Application number: CN202010739332.7A
Authority: CN
Inventors: 刘思叶; 陈德品; 代成俊; 许腾; 郭洁; 许慢
Original assignee: Nail Holding Cayman Co ltd
Current assignee: Nail Holding Cayman Co ltd
Priority date: 2020-07-28
Filing date: 2020-07-28
Publication date: 2022-02-01

Abstract

One or more embodiments of the present specification provide an information search method and apparatus. The method comprises the following steps: acquiring input data from a target object through a uniform search entry, wherein the uniform search entry corresponds to a vertical search engine with multiple dimensions; performing semantic analysis on the input data, and determining a target dimension matched with the search intention of the input data; and calling the vertical search engine of the target dimension to perform search operation.

Description

Information searching method and device

Technical Field

One or more embodiments of the present disclosure relate to the field of information processing technologies, and in particular, to an information search method and apparatus.

Background

Mobile office software has gradually become an important tool for enterprise organization management, communication collaboration and work collaboration. With the increase of various application functions in mobile office software, the search of data content plays an important role in daily office and is also an important tool for improving work efficiency.

In the related art, search contents with different dimensions correspond to different search interfaces, and when cross-dimension content search is performed, a user needs to switch a plurality of search pages and input corresponding search terms for search.

Disclosure of Invention

In view of this, one or more embodiments of the present disclosure provide an information searching method and apparatus.

To achieve the above object, one or more embodiments of the present disclosure provide the following technical solutions:

according to a first aspect of one or more embodiments of the present specification, there is provided an information search method including:

acquiring input data from a target object through a uniform search entry, wherein the uniform search entry corresponds to a vertical search engine with multiple dimensions;

performing semantic analysis on the input data, and determining a target dimension matched with the search intention of the input data;

and calling the vertical search engine of the target dimension to perform search operation.

According to a second aspect of one or more embodiments of the present specification, there is provided an information search apparatus including:

the acquisition module is used for acquiring input data from a target object through a uniform search entry, wherein the uniform search entry corresponds to a vertical search engine with multiple dimensions;

the determining module is used for performing semantic analysis on the input data and determining a target dimension matched with the search intention of the input data;

and the calling module is used for calling the vertical search engine of the target dimension to perform search operation.

According to a third aspect of one or more embodiments of the present specification, there is provided an electronic apparatus including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor implements the method of any one of the above by executing the executable instructions.

According to a fourth aspect of one or more embodiments of the present specification, there is provided a computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of any of the above-described methods.

The technical scheme provided by the embodiment of the specification can have the following beneficial effects:

in the embodiment of the specification, before a search engine performs a search operation, semantic analysis is performed on input data to determine a search intention, instead of directly performing a search using the input data as a search word, so that a user is not required to accurately input a keyword corresponding to the search intention. In addition, a unified search entry corresponding to a vertical search engine with multiple dimensions is provided, for the search requirements of contents with multiple different dimensions, a user can input data on a unified search page (for example, a home page of an application), cross-dimension search can be realized without switching the search page back and forth, data input operation is facilitated, and search experience can be improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

Drawings

Fig. 1 is a schematic diagram of an architecture of an information search system according to an exemplary embodiment.

Fig. 2a is a flowchart of an information searching method according to an exemplary embodiment.

FIG. 2b is a diagram illustrating a correspondence between a unified search entry and input components and a vertical search engine according to an exemplary embodiment.

FIG. 2c is a schematic diagram of a user interface provided by an exemplary embodiment.

FIG. 2d is a schematic illustration of another user interface provided by an exemplary embodiment.

FIG. 2e is a schematic illustration of yet another user interface provided by an exemplary embodiment.

Fig. 3 is a flow chart of another information searching method provided by an exemplary embodiment.

Fig. 4 is a schematic block diagram of a session system used in an information search method according to an exemplary embodiment.

FIG. 5 is a page schematic diagram of a dialog interaction provided by an exemplary embodiment.

Fig. 6 is a schematic diagram of a page for feeding back reminding information to a target object according to an exemplary embodiment.

Fig. 7 is a schematic block diagram of an apparatus provided in an exemplary embodiment.

Fig. 8 is a block diagram of an information search apparatus according to an exemplary embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of one or more embodiments of the specification, as detailed in the claims which follow.

It should be noted that: in other embodiments, the steps of the corresponding methods are not necessarily performed in the order shown and described herein. In some other embodiments, the method may include more or fewer steps than those described herein. Moreover, a single step described in this specification may be broken down into multiple steps for description in other embodiments; multiple steps described in this specification may be combined into a single step in other embodiments.

In an embodiment, the information search scheme of the present disclosure may be applied to an electronic device, for example, the electronic device may include any type of mobile phone, tablet device, notebook computer, Personal Digital Assistants (PDAs), wearable device (e.g., smart glasses, smart watch, etc.), and the present disclosure is not limited thereto. In the operation process, the electronic equipment can acquire input data of a user through man-machine interaction with the user and perform information search according to the input data.

Fig. 1 is a schematic diagram of an architecture of an information search system according to an exemplary embodiment. As shown in fig. 1, the system may include a server 11, a network 12, a number of electronic devices such as a cell phone 13, a cell phone 14, a cell phone 15, and the like.

The server 11 may be a physical server comprising a separate host, or the server 11 may be a virtual server carried by a cluster of hosts. In the operation process, the server 11 may operate a server-side program of a certain application to implement a relevant application function of the application, for example, when the server 11 operates a program of a mobile group office platform, the server may be implemented as a server of the mobile group office platform. In the technical solution of one or more embodiments of the present specification, the server 11 may cooperate with the client running on the mobile phone 13-15 to implement an information search system solution.

In this embodiment, the mobile group office platform not only can implement a communication function, but also can be used as an integrated functional platform with many other functions, for example, for processing internal events of a group such as an approval event (e.g., approval event such as leave request, office article claim, and finance), an attendance event, a task event, and a journal event, and for processing external events of a group such as ordering and purchasing, which is not limited in one or more embodiments of the present specification.

The handsets 13-15 are just one type of electronic device that a user may use. In fact, it is obvious that the user can also use electronic devices of the type such as: tablet devices, notebook computers, Personal Digital Assistants (PDAs), wearable devices (e.g., smart glasses, smart watches, etc.), etc., which are not limited by one or more embodiments of the present disclosure. During the operation process, the electronic device may operate a client-side program of an application to implement a relevant application function of the application, for example, when the electronic device operates a program of a mobile community office platform, the electronic device may be implemented as a client of the mobile community office platform.

It should be noted that: an application program of a client of the mobile community office platform can be pre-installed on the electronic equipment, so that the client can be started and run on the electronic equipment; of course, when an online "client" such as HTML5(Hyper Text Markup Language5, a Language description) technology is used, the client can be obtained and run without installing a corresponding application on the electronic device. And the network 12 for interaction between the handsets 13-15 and the server 11 may include various types of wired or wireless networks. In one embodiment, the Network 12 may include the Public Switched Telephone Network (PSTN) and the Internet.

Fig. 2a is a flowchart of an information searching method provided in an exemplary embodiment, which is applied to a terminal, and the method may include the following steps:

step 202, obtaining input data from the target object through the unified search entry.

The target object may be, for example, a user having information search requirements.

In this embodiment, the input data is obtained through the unified search entry, and referring to fig. 2b, the unified search entry may interface input components such as an input box in a user interface displayed by the terminal, predefined options in the user interface, a microphone, and a camera, so as to provide multiple channels for data input for the target object. The unified search entry may be, but not limited to, implemented by an Application Programming Interface (API).

It should be noted that the components such as the camera and the microphone do not necessarily need to be components installed on the terminal, but may also be based on the capabilities of other devices capable of establishing a communication connection with the terminal, such as a smart speaker, a camera/microphone of a television, a camera/microphone in a vehicle environment, a wearable device, and so on. For example, if a user starts a mobile group office platform client and inputs data in a user interface of the client through an input operation, fig. 2c is a schematic diagram of a user interface provided in an exemplary embodiment, a target object may input text data in an input box of the user interface, and a unified search entry may receive the text data as input data for information search; the target object can trigger the 'pressing and holding of the speaking control' to start a microphone of the terminal and input audio data through the microphone, the target object can also input the audio data through microphones of other equipment and send the audio data to the terminal through the other equipment, and the unified search entry can collect the audio data as input data for information search; the target object may trigger a predefined option presented by the user interface, for example, when the "meeting record query" selection is triggered, the unified search entry may use predefined data corresponding to the triggered "meeting record query" option as input data for information search. The predefined options may be, but are not limited to, presented in the user interface in the form of button controls, and each button control may display text content generated by a recommendation algorithm, where the text content corresponds to predefined data. The target object can also make a specific expression, gesture, action and the like, a camera of the terminal or a camera of other equipment acquires a picture or a video of the target object, and the unified search entry can take the picture or the video as input data. Therefore, the user can input the input data containing the content to be searched through a plurality of input operation modes such as voice input, button control triggering, spelling input and specific expressions, gestures and actions.

Referring to FIG. 2b, the unified search entry also corresponds to a vertical search engine in multiple dimensions. The multi-dimensional vertical search engine can provide search services of different application types and fields for users, for example, log search, weekly report search, set task search, contact search, historical chat record search, call record search, examination record search and the like can be performed. It should be noted that one vertical search engine may correspond to one dimension, that is, each vertical search engine performs content search of one dimension; or a plurality of vertical search engines may correspond to one dimension, for example, two vertical search engines are configured to perform log search, three vertical search engines perform examination and approval record search, and the like.

And 204, performing semantic analysis on the input data, and determining a target dimension matched with the search intention of the input data.

The semantic analysis is generally based on input data of text type, and therefore, if the input data includes data of non-text type, before performing semantic analysis on the input data, the data of non-text type needs to be converted into data of text type, so as to perform semantic analysis on the data of text type. For example, if the input data includes audio data, the audio data may be converted into text data by, but not limited to, Speech Recognition (ASR) technology.

The semantic analysis is performed on the input data, so as to determine the search intention of the target object, that is, determine the application type and the field of the search service required by the target object, and further select a vertical search engine of a target dimension matched with the search intention to perform search operation.

Each vertical search engine is pre-configured with a semantic slot matched with the search dimension of the vertical search engine, the semantic slot comprises at least one slot position, and the determination of the target dimension can be realized by means of the semantic slot. Determining a target dimension that matches the search intent may include the steps of:

and S1, performing word segmentation processing on the input data.

In another embodiment, after the word segmentation process, stop words in the word segmentation result may also be removed, where the stop words may be words without practical meaning, such as "o", "wool", "etc., punctuation marks, special symbols, etc. For example, if the input data is "find a meeting record of a certain week", the segmentation processing is performed to obtain the segmentation results of "find a meeting", "a certain week", "the" meeting record ", wherein" has no practical meaning and can be removed from the segmentation results, and the final segmentation results are "find a meeting", "a certain week" and "meeting record".

And S2, filling each phrase in the word segmentation result into each slot matched with the slot type of the semantic slot.

Suppose there are two vertical search engines, where the semantic slot of vertical search engine a contains two slot positions: an item slot and a who slot; the semantic slot of vertical search engine b contains two slot positions: a location slot and a time slot. And filling the phrases of the word segmentation result into semantic slots of the vertical search engine a and the vertical search engine b respectively, wherein the filling result is shown in tables 1 and 2.

TABLE 1

Groove position	Slot position value
		item	Meeting record
who	Certain of week

TABLE 2

Groove position	Slot position value
		location
time

And S3, determining the target dimension according to the word filling result.

As can be seen from tables 1 and 2, the phrase of the segmentation result may fill the slot of the semantic slot of the vertical search engine a but cannot fill the slot of the semantic slot of the vertical search engine b, so that it may be determined that the search intention of the input data matches the dimension of the vertical search engine a and does not match the vertical search engine b.

The slot filling rule may be set according to actual requirements, for example, the slot filling rule is set to confirm that the search intention of the input data matches the dimension of the vertical search engine corresponding to the semantic slot only when the segmentation result can fill all the slots of the semantic slot, or set to confirm that the search intention of the input data matches the dimension of the vertical search engine corresponding to the semantic slot when the segmentation result can fill a preset number of slots of the semantic slot.

It can be understood that if the input data can satisfy the slot filling rule of the multiple semantic slots, which indicates that the search intention of the input data matches with the vertical search engines of multiple dimensions, the vertical search engines of multiple dimensions may be selected as the vertical search engine of the target dimension, and the search operation is performed.

And step 206, calling a vertical search engine with a target dimension to perform search operation.

When a vertical search engine with a target dimension performs search operation, determining a phrase of a slot position filled in a semantic slot as a search word, and performing search operation aiming at the search word.

The search results obtained by the vertical search engine can be presented by, but are not limited to, the following forms: text form, voice form, predefined options, wherein each predefined option corresponds to a search result. For the Speech form, the Text-type search results may be converted into corresponding acoustic signals by Speech synthesis (Text To Speech, TTS).

In this embodiment, before the search engine performs the search operation, semantic analysis is performed on the input data to determine the search intention, instead of directly performing the search using the input data as the search word, so that the user is not required to accurately input the keyword corresponding to the search intention. In addition, a unified search entry corresponding to a vertical search engine with multiple dimensions is provided, for search requirements of multiple different application types, a user can input data on a unified search page (for example, a first page of an application), cross-application type search can be achieved without switching the search page back and forth, data input operation is facilitated, and search experience can be improved.

In another embodiment, if there are multiple target-dimension vertical search engines matching the search intent of the input data, the multiple target-dimension vertical search engines performing the search operation will obtain multiple search results. For example, if the input data is "find somebody a week", the search intention of the input data may be to find a log, a contact address, and a request for a false approval of somebody a week, there are 3 vertical search engines with different dimensions matching with the input data, and invoking the 3 vertical search engines may result in 3 search results.

Multiple search results may also be available to a vertical search engine of one dimension. For example, if the input data is "search for an approval record of a certain week", it may be determined that the search intention of the input data is to search for the approval record, the input data determines the object to which the approval record belongs, but the generation time of the approval record to be searched is not determined, and the vertical search engine may obtain a plurality of search results.

For the case of obtaining multiple search results, the historical behavior data of the user may be analyzed to determine the search preference and search historical habit of the user, and the search results are pre-processed and then displayed, where the pre-processing may be, but is not limited to, screening the search results or sorting the search results.

Or taking the input data as "find a certain in the week" as an example, assuming that the number of the vertical search engines matched with the input data is 3, the 3 vertical search engines obtain 3 search results in total, and analyzing the historical behavior data of the target object to know that the target object often checks the contact way of the certain in the week, the contact way of the certain in the week can be screened from the 3 search results and displayed, and the log of the certain in the week and the request for a fake approval are not displayed. Still alternatively, the 3 search results may be sorted, see fig. 2d, showing the search results in the following order: contact information, meeting records and request for leave examination and approval.

For the above situation of obtaining multiple search results, the multiple search results may be correspondingly displayed with the vertical search engines of multiple target dimensions, or taking the input data as "find a certain week" as an example, if the search results include a certain week telephone, an instant messaging account, a mailbox, meeting record information of 3 days in 7 months, and meeting record information of 10 days in 7 months; the phone, the instant messaging account and the mailbox are obtained by a vertical search engine with a contact searching dimension, the conference record of 7 month and 3 days and the conference record of 7 month and 10 days are obtained by a vertical search engine with a conference record searching dimension, referring to fig. 2e, the phone, the instant messaging account and the mailbox information of a certain week can be correspondingly displayed in one display area, and the conference record of 7 month and 3 days and the conference record of 7 month and 10 days are displayed in the other display area. It should be noted that the presentation manner of the search result is not limited to the form shown in fig. 2e, and the phone call, the instant messaging account, and the mailbox may be correspondingly presented in one floating window, and the conference record of day 7, month 3 and the conference record of day 7, month 10 may be displayed in another floating window.

Fig. 3 is a flowchart of another information searching method provided in an exemplary embodiment, where in this embodiment, taking information searching in a mobile community office platform as an example, referring to fig. 3, the method may include the following steps:

step 302, obtaining input data from the target object through the unified search entry.

The unified search entry corresponds to vertical search engines with multiple dimensions, and the vertical search engines with different dimensions can provide search services with different application types and fields for users. The mobile group office platform can provide, but is not limited to, log creation service, weekly report creation service, task setting service, address book service, schedule setting service, examination and approval service and the like for users, and correspondingly, vertical search engines with different dimensions can be used for searching logs, searching weekly reports, searching set tasks, searching contact ways, searching historical chat records, searching call records, searching schedule and examining and approving records and the like.

In this embodiment, the unified search portal may further interface an input box in a user interface of the mobile community office platform client, a predefined option in the user interface, a microphone of the terminal, a camera, and other components, and provide multiple channels for data input for the target object. Therefore, the target object can input the input data containing the content to be searched in various modes such as an input box of a user interface of the mobile group office platform client, predefined options displayed by the user interface, a microphone starting control and the like.

For example, if the user starts the mobile group office platform client, and inputs data in the user interface of the client through an input operation, the input data of "meeting with a certain appointment at 3 pm in the week" is input through voice, so as to trigger the unified search portal to acquire the input data of "meeting with a certain appointment at 3 pm in the week", and the input data is sent to the session system for semantic analysis.

And step 304, calling a session system to perform semantic analysis on the input data.

In this embodiment, the conversational system may perform semantic analysis on data generated by the latest input operation of the target object and data generated by the historical input operation, and determine a target dimension matching the search intention of the input data. The data generated by the latest input operation and the data generated by the historical input operation are data generated by the target object input operation in the process of the dialogue interaction.

In this embodiment, if the search intention is ambiguous, multiple rounds of dialog interaction may be performed with the target object, and the search intention may be determined according to data generated by the input operation of the target object during the multiple rounds of dialog interaction, so as to determine the target dimension matching the search intention.

Wherein the conversation system can be implemented by, but not limited to, an intelligent assistant, fig. 4 is a module diagram of a conversation system provided by an exemplary embodiment, and the conversation system includes an NLU (natural language understanding) module, a DM (dialogue management) module, and an NLG (natural language generation) module.

NLU module: the system is used for analyzing and processing input data and conversation context through a computer algorithm or a model, converting the input data and the conversation context into structured information and determining the intention of the data input by a user; wherein, the session Context (Context) refers to data generated by target object input operation in the multi-turn dialogue interaction process.

A DM module: for selecting appropriate system actions (including query, reply, and perform search operations, etc.) according to the intent recognized by the NLU module and the session context.

NLG module: the system action is used for converting the system action output by the DM module into a dialogue prompt under the condition that the system action is inquiry and reply; and in the case that the system action is to execute a search operation, calling a corresponding vertical search engine.

For example, if the user inputs input data "i want to find a certain phone in the next week" and performs semantic analysis on the input data, the search intention can be clarified, and in this case, it is not necessary to generate a dialog prompt.

If the user inputs input data of "i want to find a certain next week", the search intention may be "query contact information", may be "query history chat records", may also be "query weekly reports", and the like, and the search intention cannot be made clear, in such a case, a dialog prompt may be generated to guide the target object to input more input data capable of making the search intention clear, and the input data obtained through multiple rounds of dialog interactions makes the search intention clear.

During the interactive dialog, the dialog prompt may be presented, but is not limited to, in at least one of the following forms: text form, voice form, predefined options, wherein each predefined option corresponds to a dialog prompt content. For each turn of dialog, the user may input data by at least one of the following input actions: entering text data in an input box, entering audio data through a microphone, triggering predefined options, etc.

For example, fig. 5 is a schematic page diagram of a dialog interaction provided by an exemplary embodiment, referring to fig. 5, the input data input by the first turn of the user is "i want to find a certain week", based on this input data, the dialog system may generate dialog prompts, which in fig. 5 are presented in the form of predefined options, each of which corresponds to a dialog prompt content, and, in the case of a "call" predefined option being triggered, the predefined data 'contact address' corresponding to the predefined option is used as the input data of the target object in the current round of dialog input, when the intention is identified, the search intention is determined to be 'searching for a certain contact way in the week' according to data 'i want to find a certain in the next week' generated by the target object historical input operation and data 'contact way' generated by the latest input operation. In the dialog interaction shown in fig. 5, the search intention is clarified through 2 rounds of dialog, and in the actual use process, if the search intention cannot be clarified through 2 rounds of dialog, a dialog prompt can be further generated to guide the target object to input data, and the search intention is clarified through data of multi-round dialog interaction.

And step 306, judging whether to perform searching operation according to the semantic analysis result.

If the search intent of the input data can be determined by semantic analysis, step 308 is performed.

If it is determined through semantic analysis that the intention of the input data does not relate to information search, for example, the intention is a closing intention of the client, an operation of calling the vertical search engine is not performed, and other operations corresponding to the intention are performed.

And 308, determining a target dimension matched with the search intention, and calling a vertical search engine of the target dimension to perform search operation.

In another embodiment, in the case that multiple search results are obtained, the multiple search results may be pre-processed based on the historical behavior data of the target object and then displayed. The historical behavior data of the user is a record of the behavior of historical operations (e.g., viewing operations, clicking operations, etc.) generated by the user on the mobile community office platform client. There may be two reasons for obtaining multiple search results: a vertical search engine having a plurality of target dimensions matching the search intent of the input data; multiple search results may also be available to a vertical search engine of one dimension. For the above situation of obtaining multiple search results, the search preference and the search history habit of the user can be determined by analyzing the historical behavior data of the user, and the search results are displayed after being preprocessed, and the specific implementation process refers to the description of the corresponding part of the embodiment of the information search method shown in fig. 2, and is not described herein again.

In another embodiment, if the search result obtained by the vertical search engine of the target dimension conflicts with the target operation, the reminding information can be fed back to the target object. The input data is related to a target operation, and the target operation can be, but is not limited to, setting up a journey, creating a task and the like at a mobile community office platform client. For example, if the user inputs input data of "a meeting with a certain appointment at 3 pm in the week", semantic analysis determines that the intention of the user is a meeting appointment (target operation), a target dimension matched with the search intention of the input data is "meeting appointment query", the session system calls a vertical search engine of the meeting appointment query dimension to perform search operation, and if the user is queried to have an appointment for a meeting with other colleagues in the same time period, it indicates that the target operation of the current user conflicts with the search result, the session system feeds back the reminding information. Fig. 6 is a schematic diagram of a page provided in an exemplary embodiment for feeding back reminding information to a target object, where the reminding information may be, for example, the "does you have set up a meeting between 3 pm and liu and continue to make a reservation? The reminding information of the ' can provide dialog prompts in the forms of predefined options such as ' confirm ', ' cancel ' and the like in order to facilitate the next input operation of the user.

Fig. 7 is a schematic block diagram of an apparatus provided in an exemplary embodiment. Referring to fig. 7, at the hardware level, the apparatus includes a processor 702, an internal bus 704, a network interface 706, a memory 708, and a non-volatile storage 710, but may also include hardware required by other applications. The processor 702 reads a corresponding computer program from the non-volatile memory 710 into the memory 708 and then runs the computer program, thereby forming an information search apparatus on a logical level. Of course, besides software implementation, the one or more embodiments in this specification do not exclude other implementations, such as logic devices or combinations of software and hardware, and so on, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.

Referring to fig. 8, in a software implementation, the information searching apparatus may include:

an obtaining module 81, configured to obtain input data from a target object through a unified search entry, where the unified search entry corresponds to a vertical search engine with multiple dimensions;

a determining module 82, configured to perform semantic analysis on the input data, and determine a target dimension matching a search intention of the input data;

and the calling module 83 is configured to call the vertical search engine of the target dimension to perform a search operation.

Optionally, the input data is obtained through the unified search entry, and the input data includes at least one of:

receiving text data input by the target object in an input box corresponding to the unified search entry;

collecting audio data input by the target object aiming at the unified search entry;

and presenting predefined options corresponding to the unified search entry, and taking predefined data corresponding to the triggered predefined options as input data from the target object.

Optionally, the apparatus further comprises:

the conversion module is used for converting the non-text type data into text type data under the condition that the input data contains the non-text type data so as to perform semantic analysis on the text type data.

Optionally, the input data comprises:

data generated by the most recent input operation of the target object; or the target object is data generated by the latest input operation and data generated by the historical input operation.

Optionally, each vertical search engine is preconfigured with a semantic slot matched with the search dimension of the vertical search engine, and the semantic slot includes at least one slot position;

the determining module is specifically configured to:

performing word segmentation processing on the input data;

filling each phrase in the word segmentation result into each slot position matched with the slot position type of the semantic slot respectively;

and determining the target dimension according to the word filling result.

Optionally, the calling module is specifically configured to:

determining phrases filled into the slot positions of the semantic slots as search words;

and calling a vertical search engine of the target dimension to perform search operation aiming at the search word.

Optionally, the apparatus further comprises:

and the generating module is used for generating a dialogue prompt so as to guide the target object to input data containing the phrase matched with the slot position type of the unfilled phrase.

Optionally, in a case that the vertical search engines of multiple target dimensions all obtain search results or one target search engine obtains multiple search results, the apparatus further includes:

the acquisition module is used for acquiring historical behavior data of the target object;

the display module is used for sequencing the plurality of search results according to the historical behavior data and displaying the sequenced search results; or screening the plurality of search results according to the historical behavior data, and displaying the screened search results.

Optionally, the input data is related to a target operation; the device still includes:

and the feedback module is used for feeding back reminding information to the target object under the condition that the search result obtained by the vertical search engine of the target dimension conflicts with the target operation.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.

In a typical configuration, a computer includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement an information store by any method or technology, on which is stored a computer program (information) that, when executed by a processor, implements method steps provided by any of the embodiments described above. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in one or more embodiments of the present description to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of one or more embodiments herein. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

The above description is only for the purpose of illustrating the preferred embodiments of the one or more embodiments of the present disclosure, and is not intended to limit the scope of the one or more embodiments of the present disclosure, and any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the one or more embodiments of the present disclosure should be included in the scope of the one or more embodiments of the present disclosure.

Claims

1. An information search method, comprising:

2. The information search method of claim 1, wherein obtaining the input data through the unified search portal comprises at least one of:

3. The information search method according to claim 1, further comprising:

in the case where the input data contains non-text type data, converting the non-text type data into text type data to perform semantic analysis on the text type data.

4. The information search method according to claim 1, wherein the input data includes:

5. The information search method according to claim 1, wherein each vertical search engine is pre-configured with a semantic slot matching its search dimension, the semantic slot comprising at least one slot position;

performing semantic analysis on the input data to determine a target dimension matching the search intent of the input data, comprising:

performing word segmentation processing on the input data;

and determining the target dimension according to the word filling result.

6. The information search method of claim 5, wherein the invoking of the vertical search engine of the target dimension to perform a search operation comprises:

7. The information search method according to claim 5, further comprising, in a case where the slot of the semantic slot is not filled up:

and generating a dialog prompt to guide the target object to input data containing the phrase matched with the slot type of the unfilled phrase.

8. The information search method according to claim 1, wherein in a case where the vertical search engines of a plurality of target dimensions all obtain the search result or one target search engine obtains a plurality of the search results, the method further comprises:

acquiring historical behavior data of the target object;

sequencing the plurality of search results according to the historical behavior data, and displaying the sequenced search results; or screening the plurality of search results according to the historical behavior data, and displaying the screened search results.

9. The information search method according to claim 1, wherein in a case where the vertical search engines of a plurality of target dimensions each obtain a search result, the method further comprises:

and correspondingly displaying the plurality of search results and the vertical search engines with the plurality of target dimensions.

10. The information search method according to claim 1, wherein the input data is related to a target operation; the method further comprises the following steps:

and under the condition that the search result obtained by the vertical search engine of the target dimension is in conflict with the target operation, feeding back reminding information to the target object.

11. An information search apparatus, comprising:

12. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor implements the method of any one of claims 1-10 by executing the executable instructions.

13. A computer-readable storage medium having stored thereon computer instructions, which, when executed by a processor, carry out the steps of the method according to any one of claims 1-10.