Information search method, related device and communication system

Abstract

The invention provides an information search method, a related device and a communication system. The electronic equipment can search the related file according to the semantics of the query statement, extract the information to be searched by the query statement from the related file and provide the information to the user, so that the user can directly obtain the information to be searched by himself / herself through search operation. The electronic equipment can also provide a function control using the searched information, so that the user can quickly use the searched information. According to the method, the information searching and obtaining operation of the user is simplified, and the information obtaining efficiency of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and in particular to an information search method, related devices and a communication system. Background Art

[0002] Electronic devices such as mobile phones and tablets are increasingly used in daily life. Users often save a lot of information locally or in the cloud (such as cloud disks, cloud storage spaces, etc.) on electronic devices, such as ID card information, bank card information, address information, work documents, etc. When users need to use this information, they usually have to perform multiple operations in the electronic device, search and open the page where the relevant information is located, and then manually extract the required information from the page. The above operation of obtaining information is cumbersome and the user experience is poor. Summary of the invention

[0003] The present application provides an information search method, a related device and a communication system. The method can simplify the user's operation of searching for information and improve the user's efficiency in obtaining information by extracting the information that the user wants to search from a file for the user to use.

[0004] In a first aspect, the present application provides an information search method, wherein an electronic device receives a first operation, the first operation is used to search for a first content; in response to the first operation, the electronic device displays a first search result on a first page, the first search result is searched based on the first content, and the first search result includes first information extracted from a first file; the electronic device displays one or more first function controls for using the first information on the first page, the one or more first function controls are related to the type of the first information.

[0005] The first file may be a file stored locally in the electronic device and / or in the cloud. The files in the cloud may include files in a cloud storage space associated with the electronic device. For example, a device account is logged into the electronic device. The files in the cloud may include files in the cloud storage space of the device account. For another example, a cloud disk application account is logged into the cloud disk application of the electronic device. The files in the cloud may include files in the cloud storage space of the cloud disk application account. Optionally, the files in the cloud may also include web page content on the Internet (such as news, products, addresses, papers, etc. on the Internet).

[0006] It can be seen from the above method that when the information that the user wants to search exists in a file, the electronic device can extract the information that the user wants to search from the file, and display one or more function controls on the display page of the search results for the user to use the above searched and extracted information. In this way, the user can obtain the information he wants to search through a single search operation, without having to open the corresponding file after the search and then manually extract the information he needs from the file. The above method simplifies the user's operation of searching for information and improves the efficiency of the user in obtaining information.

[0007] In combination with the first aspect, in some embodiments, the first operation includes an operation of calling out a first search box in the electronic device and entering first content in the first search box; or, the first operation includes an operation of selecting the first content and searching; or, the first operation includes an operation of entering a first symbol at a first position associated with the first content; or, the first operation includes an operation of a query control associated with the first content.

[0008] For example, the operation of calling the first search box can refer to the present application Figure 1A The first page can be a page containing a first search box that is called out by the above-mentioned sliding down operation. The user can enter a query statement in the first search box to instruct the electronic device to search for the content that the user wants to search. The first search box can refer to Figure 3A The search box 311 is shown. The first content may be a query statement.

[0009] The above operation of selecting the first content and searching can refer to this application Figure 4A The operation shown is to select text 411A and click on search control 412A. The text 411A may be the first content (ie, the query statement) mentioned above. The first page may be a display page of the first content.

[0010] The first position associated with the first content may be, for example, the end of the first content. The first symbol may be a single symbol. For example, " / " or "@" or "#", etc. The first symbol may also be a combination symbol. For example, " / #" or "@#", etc. The first position and the first symbol may refer to the present application. Fig. 6A The user interface 610 shown is a first page that may be a display page of the first content.

[0011] The query control associated with the first content may be, for example, a query control displayed at the end of the first content. Optionally, the query control may be displayed by the electronic device in response to a preset operation. Fig. 7A The query control 712 is shown. The first page may be a display page of the first content.

[0012] It can be seen that users can perform query operations in a variety of ways, which can facilitate users to quickly search and obtain the information they need in different scenarios.

[0013] In combination with the first aspect, in some embodiments, the first search result further includes one or more of the following: the name of the first file, the application to which the first file belongs, and the content of the first file including the first information.

[0014] The content of the first information in the first file may be, for example, the paragraph in which the first information is located in the first file. The content of the first information in the first file may facilitate the user to view the context of the first information in the first file. In this way, the user may more accurately determine whether the first information is the information he needs to find.

[0015] In combination with the first aspect, in some embodiments, in response to the first operation, the electronic device also displays a second search result on the first page, where the second search result is searched based on the first content, and the second search result includes second information extracted from the second file; the electronic device displays one or more second function controls for using the second information on the first page, and the one or more second function controls are related to the type of the second information.

[0016] It can be seen that when multiple search results are found according to the query statement, the electronic device can provide the multiple search results for the user to use. In addition, the electronic device can also display the specific content of the source of the multiple search results. This makes it convenient for the user to check which of the multiple search results are needed by the user.

[0017] In combination with the first aspect, in some embodiments, the one or more first functional controls include a first copy control, and the first copy control is used to copy the first information.

[0018] The first copy control can refer to this application Figure 3A Copy control 312C is shown.

[0019] In combination with the first aspect, in some embodiments, the type of the first information is a telephone number, and one or more first function controls include a dialing control, which is used to dial the telephone number corresponding to the first information; or, the type of the first information is an address, and one or more first function controls include a navigation control, which is used to navigate to the address corresponding to the first information; or, the type of the first information is a bank card number, and one or more first function controls include a transfer control, which is used to transfer money using the bank card number corresponding to the first information.

[0020] In combination with the first aspect, in some embodiments, the first content is located on a first page, one or more first function controls include a first insertion control, and the electronic device receives an operation on the first insertion control and inserts the first information on the first page.

[0021] The first insertion control can refer to this application Figure 6B Insert control 618A or insert control 619A is shown.

[0022] In combination with the first aspect, in some embodiments, the electronic device receives a second operation, the second operation is used to search for second content, and the second content is located on a second page; in response to the second operation, the electronic device displays a third search result on the second page, the third search result is searched based on the second content, and the third search result includes a first option corresponding to a third file; in response to the operation on the first option, the electronic device inserts the third file on the second page.

[0023] The first option above may be equivalent to an insert control for inserting a third file. Fig. 6A Insertion control 616A is shown.

[0024] The third file may be inserted into the second page as a link. Alternatively, the third file may be inserted into the second page in other forms. The embodiment of the present application does not limit the form in which the third file is inserted into the second page.

[0025] It can be seen that in the text editing scenario, users can search for the information they need (such as text information, image information, files, etc.) during the text editing process, and quickly insert the searched information into the text editing content through the insert control. This can improve the efficiency of user text editing.

[0026] In combination with the first aspect, in some embodiments, the electronic device receives an operation on the inserted first information on the first page and displays the source of the first information, where the source of the first information includes one or more of the following: the name of the first file, the application to which the first file belongs, and the content of the first information contained in the first file.

[0027] It can be seen that the first information searched and inserted into the first page can also support user interaction. The user can view the source of the first information by clicking on the inserted first information (or other operations on the first information).

[0028] In combination with the first aspect, in some embodiments, an electronic device receives a first instruction from a user, where the first instruction is used to instruct to extract information from a fourth file and fill it into a third page, where the third page includes a first input box; according to the first instruction, the electronic device fills in third information in the first input box, where the third information is information extracted from the fourth file and matches the first input box.

[0029] The first instruction may be a voice instruction input by a user, or a text instruction input by a user in an electronic device. Fig.8D Information 824A is shown.

[0030] The electronic device may use the description information of the first input box as a query statement, and search for corresponding information from the fourth file according to the semantics of the query statement, thereby filling the searched information into the first input box. The description information of the first input box may be used to indicate information about the content to be input in the first input box.

[0031] The third page may include more input boxes, not limited to the first input box. The electronic device may use the description information of these input boxes as a query statement to search the fourth file for information that can be filled in the input boxes.

[0032] It can be seen that the point itself can be combined with applications such as voice assistants to recognize user instructions, extract information from the specified file and fill it into the target area. In this way, when the information in the specified file needs to be filled into the target area, the user can directly issue search and fill instructions to the electronic device without manually copying and pasting. The above method simplifies the user's operations of searching, obtaining and filling in information, and improves the efficiency of the user in obtaining information.

[0033] In combination with the first aspect, in some embodiments, before the electronic device displays the first search result, the electronic device determines file content information and file attribute information based on the first content, the file content information represents the semantic limitation of the information to be searched for the first content in the first content, and the file attribute information represents the attribute limitation of the information to be searched for the first content in the first content; the electronic device determines a first semantic vector of the first content based on the file content information; the electronic device searches for one or more files based on the file attribute information, and obtains semantic vectors corresponding to the one or more files, the one or more files including the first file; the electronic device calculates the similarity between the semantic vectors corresponding to the one or more files and the first semantic vector, and selects a second semantic vector corresponding to the first file based on the similarity, the second semantic vector being the semantic vector with the highest similarity among the semantic vectors whose similarity to the first semantic vector is higher than a first threshold; the electronic device extracts the first information from the first file based on the first content.

[0034] It can be seen that the user can enter a query statement in the electronic device to quickly query and obtain the information they want to query. The electronic device can extract the information that the user wants to search from the files locally on the electronic device and / or in the cloud for the user to use according to the semantics of the query statement. In this way, the user can obtain the information he wants to search through a single search operation, without having to open the corresponding file after the search and then manually extract the information he needs from the file. The above method simplifies the operation of the user searching for information and improves the efficiency of the user in obtaining information.

[0035] The above-mentioned file content information determined by the first content may represent the semantic limitation of the information to be searched for by the first content in the first content. In other words, the file content information may be a condition that limits the semantics or meaning of the search results, which can be used by the electronic device to search for the search results required by the query statement according to the semantics. The above-mentioned file attribute information determined by the first content may represent the attribute limitation of the information to be searched for by the first content in the first content. The embodiment of the present application does not limit the content contained in the file attribute information. For example, the file attribute information may include one or more of the following: creation time, creation location, creation user, APP to which it belongs, modification time, number of modifications, file size, storage location, etc. In other words, the file content information may be a condition that limits the attributes of the file to which the search results belong, which can be used by the electronic device to search for the file to which the search results required by the query statement belong according to the attributes, so that the search results can be extracted from the file.

[0036] In some embodiments, a file may contain multiple contents (or multiple data fragments). The electronic device may split the contents in a file and determine the semantic vectors associated with each data fragment after the split. In this way, a file may be associated with multiple semantic vectors. For example, a text file may contain multiple paragraphs of text. The electronic device may split the text file according to paragraphs, and extract the semantic vector associated with each paragraph through a semantic vector extraction model. Alternatively, a text file may contain multiple chapters. The electronic device may split the text file according to chapters, and extract the semantic vector associated with each chapter through a semantic vector extraction model. For another example, a table file may contain multiple rows of data. The electronic device may split the table file by row, and extract the semantic vector associated with each row of data in the table file through a semantic vector extraction model. For another example, a presentation document may contain multiple pages of data. The electronic device may split the presentation file by page, and extract the semantic vector associated with each page of data in the presentation document through a semantic vector extraction model.

[0037] It is understandable that the themes to be expressed in different paragraphs or chapters in a text file may be different. For example, the first paragraph of a text file introduces the types of cats, and the second paragraph introduces the living habits of cats. The information to be expressed by data in different rows of a table file may also be different. For example, the first row of a table file records the sales volume of product 1, and the second row records the sales volume of product 2. The themes to be expressed by the contents of different pages in a presentation document may also be different. For example, the first page of a presentation document introduces the background technology of the solution, and the second page introduces the specific implementation method of the solution. The above-mentioned splitting of the file and then extracting the semantic vectors of the split data segments can facilitate electronic devices to more accurately find the information that users want to search for when searching for information.

[0038] Among them, the above-mentioned first file may correspond to multiple semantic vectors. These multiple semantic vectors may respectively correspond to different data segments (such as different text paragraphs) in the first file. These multiple semantic vectors may include a second semantic vector. The second semantic vector may correspond to data segment 1 in the first file. When it is determined that the second semantic vector is the semantic vector with the highest similarity among the semantic vectors whose similarity with the first semantic vector is higher than the first threshold, the electronic device can extract the first information from the data segment 1 of the first file according to the first content.

[0039] In some embodiments, the above-mentioned determination of the file content information and the file attribute information by the first content may be implemented by a language model. Among them, the semantic model may be deployed in a cloud server. The electronic device may send the first content to the cloud server. Then, the cloud server may determine the file content information and the file attribute information from the first content by using the language model. The cloud server may send the file content information and the file attribute information to the electronic device. Alternatively, the language model may be stored in the electronic device. When the first content is acquired, the electronic device may determine the file content information and the file attribute information from the first content by using the language model.

[0040] In some embodiments, the extracting of the first information from the first file according to the first content may also be achieved through a language model.

[0041] In some embodiments, the electronic device can determine that the second semantic vector is the most similar to the first semantic vector by finding the semantic vectors corresponding to the one or more files in the semantic vector database based on the first semantic vector. The semantic vector database may store semantic vectors associated with files locally on the electronic device 1 and / or in the cloud. Among them, a file may be associated with one or more semantic vectors. The above-mentioned semantic vector database may be established by the electronic device, or it may also be established by a server. In some embodiments, when the files stored locally on the electronic device change, or the files stored in the cloud storage space associated with the electronic device change, the electronic device may update the above-mentioned semantic vector database. The above-mentioned file changes may include but are not limited to: newly added files, changes in the content of the files, deletion of existing files, etc.

[0042] In a second aspect, the present application provides an electronic device, which may include a memory and a processor. The memory may be used to store a computer program. The processor may be used to call the computer program so that the electronic device executes any possible implementation method in the first aspect.

[0043] In a third aspect, the present application provides a computer-readable storage medium, comprising instructions, which, when executed on an electronic device, enable the electronic device to execute any possible implementation method in the first aspect.

[0044] In a fourth aspect, the present application provides a computer program product, which may include computer instructions. When the computer instructions are run on an electronic device, the electronic device executes any possible implementation method in the first aspect.

[0045] In a fifth aspect, the present application provides a chip, which is applied to an electronic device, and the chip includes one or more processors, and the processor is used to call computer instructions to enable the electronic device to execute any possible implementation method as in the first aspect.

[0046] It can be understood that the electronic device provided in the second aspect, the computer-readable storage medium provided in the third aspect, the computer program product provided in the fourth aspect, and the chip provided in the fifth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1A to Figure 1D is a schematic diagram of some information search scenarios provided by embodiments of the present application;

[0048] Figure 2A is a schematic diagram of the hardware structure of an electronic device 100 provided in an embodiment of the present application;

[0049] Figure 2B is a software structure block diagram of an electronic device 100 provided in an embodiment of the present application;

[0050] Figure 3A to Figure 3D is a schematic diagram of some information search scenarios provided by embodiments of the present application;

[0051] Figure 4A to Figure 4D is a schematic diagram of other information search scenarios provided by embodiments of the present application;

[0052] Figure 5A to Figure 5D is a schematic diagram of other information search scenarios provided by embodiments of the present application;

[0053] Figure 6A to Figure 6C is a schematic diagram of other information search scenarios provided by embodiments of the present application;

[0054] Figure 7A to Figure 7G is a schematic diagram of other information search scenarios provided by embodiments of the present application;

[0055] Figure 8A to Figure 8E is a schematic diagram of other information search scenarios provided by embodiments of the present application;

[0056] Fig. 9 It is a flow chart of a method for establishing a semantic vector database provided in an embodiment of the present application;

[0057] Fig.10 is a flow chart of an information search method provided by an embodiment of the present application;

[0058] Fig.11 It is a schematic diagram of the architecture of a communication system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the embodiments of the present application, the terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to be used as limitations on the present application. As used in the specification and the appended claims of the present application, the singular expressions "a", "said", "above", "the" and "this" are intended to also include expressions such as "one or more", unless there is a clear indication to the contrary in the context. It should also be understood that in the following embodiments of the present application, "at least one", "one or more" refer to one or more (including two). The term "and / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist; for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in a "or" relationship.

[0060] References to "one embodiment" or "some embodiments" etc. described in this specification mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Thus, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways. The term "connection" includes direct connection and indirect connection, unless otherwise specified. "First" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated.

[0061] In the embodiments of the present application, the words "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0062] The term "user interface (UI)" in the following embodiments of the present application refers to the medium interface for interaction and information exchange between an application (APP) or an operating system (OS) and a user, which realizes the conversion between the internal form of information and the form acceptable to the user. The user interface is a source code written in a specific computer language such as Java and extensible markup language (XML). The interface source code is parsed and rendered on an electronic device and finally presented as content that can be recognized by the user. The commonly used form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed in a graphical manner. It can be a visual interface element such as text, icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, widgets, etc. displayed on the display screen of an electronic device.

[0063] The following introduces an information search scenario provided by this application.

[0064] Figure 1A to Figure 1D The following is a schematic diagram showing some information search scenarios.

[0065] like Figure 1A As shown, the electronic device 100 may display a user interface 210. The user interface 210 may be a desktop of the electronic device 100, which may display one or more application icons. The above application icons may be used to open the corresponding APP. In some embodiments, in response to Figure 1A The electronic device 100 can call a global search application to display the user interface 210 by sliding downward. Figure 1B The user interface 220 shown. The global search application can be used to search local content of the electronic device 100. The local content of the electronic device 100 can represent the content stored in the electronic device 100. Optionally, the global search application can also be used to search web page content. Optionally, the global search application can also be used to search content in a cloud storage space associated with the electronic device 100. The embodiment of the present application does not limit the operation method of calling the global search application.

[0066] like Figure 1B As shown, the user interface 220 may include a search box 221. The user may enter the content that he wants to search for in the search box 221. For example, if the user wants to search for ID card information, he may enter the text content "ID card" in the search box 221. The electronic device 100 may search according to the content in the search box 221 and display the search results. Here, the electronic device 100 searches for pictures related to ID cards in the gallery application as an example. The electronic device 100 may search for ID cards locally and / or in the cloud. The search results may include Figure 1B The following are pictures 222 and 223. Both pictures 222 and 223 are pictures of ID cards. In response to an operation on picture 222, such as a click operation, the electronic device 100 may display Figure 1C User interface 230 is shown.

[0067] like Figure 1C As shown, the user interface 230 may be an interface of a gallery application. The user interface 230 may include a picture 231. The picture 231 is Figure 1B In some embodiments, in response to an operation on the picture 231, such as a long press operation, the electronic device 100 can perform text recognition on the picture 231 and display the text. Figure 1D The user interface 240 is shown. The embodiment of the present application does not limit the above operations for performing text recognition.

[0068] like Figure 1D The user interface 240 shown may include a picture 241 and a text extraction display area 242. The picture 241 is the aforementioned Figure 1C The picture 231 (i.e. Figure 1BThe text extraction display area 242 can be used to display the text content extracted from the above-mentioned picture 241. It can be seen that the text extraction display area 242 can include the name, gender, address and ID number on the ID card in the picture 241. The user can select part or all of the extracted text content. For example, in response to the operation of selecting the ID card number, the electronic device 100 can display Figure 1D The selected mark 242A shown. The selected mark 242A can indicate that the ID number "123***" is in a selected state. The text extraction display area 242 can also include a copy control 242B. In response to an operation on the copy control 242B, such as a click operation, the electronic device 100 can copy the ID number indicated by the selected mark 242A.

[0069] By the above Figure 1A to Figure 1D As can be seen from the scenario shown, when a user wants to use an ID card number (e.g., to send his or her ID card number to others), but the electronic device 100 stores a picture of the ID card, the user needs to first search for the picture of the ID card and click on the picture to enter the display interface of the picture in the gallery application. Then, the user operates the picture in the gallery application to trigger the electronic device 100 to perform text recognition on the picture. Finally, the user selects the ID card number and copies it.

[0070] It is understandable that users search for information in order to use the information they have searched for. Figure 1A to Figure 1D In the scenario shown, after the user performs a search operation, the search results provided to the user by the electronic device 100 are often not information that the user can directly use. In the above scenario, the user's operation of searching and obtaining information is relatively cumbersome, and it is difficult for the user to quickly obtain the information he needs. The user's experience when searching for information is poor.

[0071] The present application provides an information search method. Among them, the electronic device can recognize the semantics of a query statement. The query statement can represent the content used to instruct the electronic device to search. The electronic device can search for relevant files based on the semantics of the query statement, and extract the information to be searched by the query statement from the relevant files and provide it to the user, so that the user can directly obtain the information he wants to search through the search operation. In some embodiments, the electronic device can also provide a function control for using the information based on the purpose of the above-mentioned searched information, so that the user can quickly use the information he searched for. For example, if the above-mentioned information is address information, the electronic device can provide a navigation control so that the user can navigate to the address corresponding to the above-mentioned address information. For another example, if the above-mentioned information is a bank card number, the electronic device can provide a transfer control so that the user can use the bank card corresponding to the above-mentioned bank card number to transfer money.

[0072] It can be seen from the above method that when the information that the user wants to search exists in a file, the electronic device can extract the information that the user wants to search from the file for the user to use. In this way, the user can obtain the information that he wants to search through a single search operation, without having to open the corresponding file after the search and then manually extract the information he needs from the file. The above method simplifies the operation of the user to search and obtain information, and improves the efficiency of the user to obtain information.

[0073] The structure of the electronic device 100 involved in this application is introduced below.

[0074] Figure 2A The schematic diagram of the hardware structure of the electronic device 100 is exemplarily shown.

[0075] like Figure 2A As shown, the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0076] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0077] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0078] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0079] The processor 110 may also be provided with a memory for storing instructions and data. In some examples, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0080] In the present application, a computer program may be stored in the memory, which is used to enable the controller or processor to implement the information search method of the present application through an interface or protocol.

[0081] Exemplarily, the computer program stored in the memory can be used to: obtain a query statement, determine the semantics of the query statement, search for relevant files from the local and / or cloud of the electronic device 100 based on the semantics of the query statement, and extract the information to be queried by the query statement from the relevant files, identify the purpose of the information to be queried by the query statement, and provide corresponding functional controls for the user to use the above-mentioned queried information.

[0082] The USB interface 130 is an interface that complies with USB standard specifications, and may be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface 130 may be used to connect a charger to charge the electronic device 100, or may be used to transmit data between the electronic device 100 and a peripheral device. It may also be used to connect headphones to play audio through the headphones.

[0083] The charging management module 140 is used to receive charging input from a charger. The charger can be a wireless charger or a wired charger. While the charging management module 140 charges the battery 142, it can also power the electronic device through the power management module 141.

[0084] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140 to power the processor 110, the internal memory 121, the external memory, the display screen 194, the camera 193, and the wireless communication module 160.

[0085] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0086] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0087] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, etc. the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1.

[0088] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0089] The electronic device 100 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which is connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering.

[0090] The display screen 194 is used to display images, videos, etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194 , where N is a positive integer greater than 1.

[0091] The electronic device 100 can realize the shooting function through ISP, camera 193, video codec, GPU, display screen 194 and application processor.

[0092] The ISP is used to process data fed back by the camera 193. For example, when taking a photo, the shutter is opened, light is transmitted to the camera photosensitive element through the lens, and the light signal is converted into an electrical signal. The camera photosensitive element transmits the electrical signal to the ISP for processing and converts it into an image visible to the naked eye.

[0093] The camera 193 is used to capture still images or videos. In some embodiments, the electronic device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.

[0094] The digital signal processor is used to process digital signals, and can process not only digital image signals but also other digital signals. For example, when the electronic device 100 is selecting a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0095] NPU is a neural network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transmission mode between neurons in the human brain, it can quickly process input information and can also continuously self-learn. NPU can realize applications such as intelligent cognition of electronic device 100, such as image recognition, face recognition, voice recognition, text understanding, text generation, etc.

[0096] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function, such as storing music, video and other files in the external memory card.

[0097] The internal memory 121 can be used to store computer executable program codes, which include instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0098] The electronic device 100 can implement audio functions such as music playing and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.

[0099] The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some examples, the audio module 170 can be arranged in the processor 110, or some functional modules of the audio module 170 can be arranged in the processor 110. The speaker 170A, also known as the "speaker", is used to convert audio electrical signals into sound signals. The receiver 170B, also known as the "earpiece", is used to convert audio electrical signals into sound signals. The microphone 170C, also known as the "microphone" or "microphone", is used to convert sound signals into electrical signals. The headphone jack 170D is used to connect wired headphones.

[0100] The sensor module 180 may include a pressure sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a gravity sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, a bone conduction sensor, and the like.

[0101] Among them, the gyroscope sensor can be used to determine the motion posture of the electronic device 100. In some embodiments, the angular velocity of the electronic device 100 around three axes (i.e., x, y, and z axes) can be determined by the gyroscope sensor. The electronic device 100 can determine the offset angle of the electronic device 100 through the gyroscope sensor.

[0102] The acceleration sensor can detect the magnitude of acceleration in all directions (generally three axes) of the electronic device 100. In some embodiments, the acceleration sensor can be used to identify the posture of the electronic device 100, and can be applied to applications such as horizontal and vertical screen switching and pedometers.

[0103] The gravity sensor can be used to determine the tilt angle of the electronic device 100 relative to the horizontal plane. In some embodiments, the screen state of the electronic device 100 can be determined by the gravity sensor, so that the screen is adjusted to keep it horizontal.

[0104] In some embodiments, the electronic device 100 may determine the moving distance of the electronic device 100 within a period of time by using an acceleration sensor and a gravity sensor.

[0105] The buttons 190 include a power button, a volume button, etc. The motor 191 can generate a vibration prompt. The indicator 192 can be an indicator light, which can be used to indicate the charging status, power change, messages, missed calls, notifications, etc.

[0106] The SIM card interface 195 is used to connect a SIM card. The SIM card can be connected to and separated from the electronic device 100 by inserting it into the SIM card interface 195 or removing it from the SIM card interface 195. The electronic device 100 can support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The electronic device 100 interacts with the network through the SIM card to implement functions such as calls and data communications. In some examples, the electronic device 100 uses an eSIM, i.e., an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100.

[0107] The software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. Taking the system as an example, the software structure of the electronic device 100 is exemplified.

[0108] Figure 2BThe software structure block diagram of the electronic device 100 is exemplarily shown.

[0109] The layered architecture divides the software into several layers, each with a clear role and division of labor. The layers communicate with each other through software interfaces. The system is divided into four layers, from top to bottom: application layer, application framework layer, Android Runtime and system library, and kernel layer.

[0110] The application layer can include a series of application packages.

[0111] like Figure 2B As shown, the application package may include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, global search application, short message, etc. Among them, the global search application can be used to search for content in the local and / or cloud of the electronic device 100. The above-mentioned search for content in the local electronic device 100 may mean searching for content stored in the electronic device 100, for example, pictures in the gallery application of the electronic device 100, memo information in the memo application, documents in the file application, etc. The above-mentioned search for content in the cloud may include searching for content in the cloud storage space associated with the electronic device 100. For example, a device account is logged in to the electronic device 100. The electronic device 100 can search the cloud storage space of the device account. For another example, a cloud disk application account is logged in to the cloud disk application of the electronic device 100. The electronic device 100 can search the cloud storage space of the cloud disk application account. The above-mentioned cloud storage space may also be called a cloud disk, a network disk, etc. Optionally, the above-mentioned search for content in the cloud may also include searching for web page content. The above-mentioned web page content may represent content on the Internet, for example, news, goods, addresses, papers, etc. on the Internet. The embodiment of the present application does not limit the name of the above-mentioned global search application. For example, the global search application may also be called an intelligent search application, a search service, or the like.

[0112] The application framework layer provides API and programming framework for the applications in the application layer. The application framework layer includes some predefined functions.

[0113] like Figure 2B As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, an activity manager, and the like.

[0114] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0115] Content providers are used to store and retrieve data and make it accessible to applications. The data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0116] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0117] The phone manager is used to provide communication functions of the electronic device 100, such as management of call status (including connecting, hanging up, etc.).

[0118] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0119] The notification manager enables applications to display notification information in the status bar (such as the pull-down notification bar). It can be used to convey notification-type messages and can automatically disappear after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, an electronic device vibrates, an indicator light flashes, etc.

[0120] The activity manager is responsible for managing activities, starting, switching, and scheduling components in the system, as well as managing and scheduling applications. The activity manager can be called by upper-level applications to open corresponding activities.

[0121] Android Runtime includes core libraries and virtual machines. Android Runtime is responsible for scheduling and management of the Android system.

[0122] The core library consists of two parts: one part is the function that needs to be called by the Java language, and the other part is the Android core library.

[0123] The application layer and the application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0124] The system library may include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0125] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0126] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0127] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0128] A 2D graphics engine is a drawing engine for 2D drawings.

[0129] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.

[0130] The following introduces some information search scenarios provided by embodiments of the present application.

[0131] Figure 3A to Figure 3D The following is a schematic diagram showing some information search scenarios.

[0132] 1. Figure 3A The example shows a scenario where a user searches for an ID card number.

[0133] like Figure 3A As shown, the electronic device 100 may display a user interface 310. The user interface 310 may be in response to the aforementioned Figure 1A The user interface 310 is displayed by sliding down on the desktop. The embodiment of the present application does not limit the operation method of calling up the user interface 310. The user interface 310 may include a search box 311. The user may enter the content to be searched in the search box 311. The electronic device 100 may determine the content entered in the search box 311 as a query statement and search according to the query statement.

[0134] The user can enter "Zhang San's ID number" in the search box 311 to search for the ID number of the user named Zhang San. The content in the search box 311 is "Zhang San's ID number". The electronic device 100 can determine that the query statement is "Zhang San's ID number". The electronic device 100 can perform semantic recognition on the query statement to find files containing Zhang San's ID number. The specific implementation method of the above-mentioned semantic recognition of the query statement and searching for files based on the semantics will be introduced in the subsequent embodiments. It will not be expanded here.

[0135] For example, the electronic device 100 searches for a photo of an ID card containing the ID number of Zhang San. The electronic device 100 can display Figure 3A The search result display box 312 is shown. The search result display box 312 may include an ID number 312A, a search information source 312B, a copy control 312C, a picture 312D, and a selection mark 312E. Among them, the picture 312D may be a photo of an ID card containing Zhang San’s ID number searched by the electronic device 100. The ID number 312A may be extracted from the picture 312D. The selection mark 312E on the picture 312D may be used to indicate that the above-mentioned ID number 312A is the content indicated by the selection mark 312E. The search information source 312B may be used to indicate the source of the searched information (i.e., the ID number 312A). For example, the source may be an APP. The search information source 312B is Figure 3A The "Gallery" shown may indicate that the ID number 312A is searched from the gallery application. Not limited to APP, the source of the above search information may also include the file name, storage path, etc. The embodiment of the present application does not limit the source of the search information. Optionally, the search result display box 312 may not include the selection mark 312E.

[0136] The copy control 312C can be used to copy the ID number 312A. In response to an operation on the copy control 312C, such as a click operation, the electronic device 100 can copy the ID number 312A (i.e., Zhang San's ID number) to the clipboard. In this way, the user can paste the above-mentioned Zhang San's ID number at a desired location.

[0137] Depend on Figure 3A It can be seen that when a user wants to use an ID card number, the user can directly obtain and use the ID card number of the target user by searching for the ID card number of the target user. In this way, the user does not need to open the display page of the ID card photo and then manually extract the ID card number from the ID card photo. The above method can facilitate users to quickly obtain the information they want to search for, and improve the user's experience in information search.

[0138] 2. Figure 3B The example shows a scenario where a user searches for a bank card number.

[0139] like Figure 3B As shown, the electronic device 100 may display a user interface 320. The user interface 320 may be in response to the aforementioned Figure 1A The user interface 320 may include a search box 321. The search box 321 may refer to the aforementioned Figure 3A Search box 311 is shown.

[0140] The user can enter "AA bank card number" in the search box 321 to search for the bank card number of the AA bank. The content in the search box 321 is "AA bank card number". The electronic device 100 can determine that the query statement is "AA bank card number".

[0141] For example, the electronic device 100 can search for bank card photos containing the AA bank card number according to the above query statement. The electronic device 100 can display Figure 3B The search result display box 322 is shown. The search result display box 322 may include a bank card number 322A, a search information source 322B, a transfer control 322C, a copy control 322D, a picture 322E, and a selection mark 322F. Among them, the picture 322E may be a bank card photo containing an AA bank card number searched by the electronic device 100. The bank card number 322A may be extracted from the picture 322E. The selection mark 322F on the picture 322E may be used to indicate that the above-mentioned bank card number 322A is the content indicated by the selection mark 322F. The search information source 322B may be used to indicate the source of the searched information (i.e., the bank card number 322A). For example, the search information source 322B is Figure 3B The “Gallery” shown may indicate that the bank card number 322A is searched from a gallery application.

[0142] The transfer control 322C may be used to open a page for transferring money using the bank card corresponding to the bank card number 322A.

[0143] The copy control 322D can be used to copy the bank card number 322A. In response to an operation on the copy control 322D, such as a click operation, the electronic device 100 can copy the bank card number 322A (i.e., the bank card number of AA Bank) to the clipboard. In this way, the user can paste the bank card number of the AA Bank at a desired location, for example, to send the bank card number to other users.

[0144] Not limited to the transfer control 322C and the copy control 322D, the electronic device 100 may also provide more or fewer functional controls for using the above-mentioned bank card number 322A.

[0145] Depend on Figure 3BIt can be seen that when a user wants to use a bank card number, the user can directly obtain and use the bank card number of the target bank card by searching for the bank card number of the target bank card. In this way, the user does not need to open the display page of the bank card photo and then manually extract the bank card number from the bank card photo. The above method can facilitate users to quickly obtain the information they want to search for, and improve the user's experience in information search.

[0146] 3. Figure 3C The example shows a scenario where a user searches for an address.

[0147] like Figure 3C As shown, the electronic device 100 may display a user interface 330. The user interface 330 may be in response to the aforementioned Figure 1A The user interface 330 may include a search box 331. The search box 331 may refer to the aforementioned Figure 3A Search box 311 is shown.

[0148] The user can enter "BB hotel address" in the search box 331 to search for the address of the BB hotel. The content in the search box 331 is "BB hotel address". The electronic device 100 can determine that the query statement is "BB hotel address".

[0149] For example, the electronic device 100 can search for memo information containing the address of BB Hotel according to the above query statement. The electronic device 100 can display Figure 3C The search result display box 332 is shown. The search result display box 332 may include an address 332A, a search information source 332B, a navigation control 332C, a copy control 332D, a memo display area 332E, and a selection mark 332F. Among them, the memo display area 332E may display the memo information containing the address of the BB Hotel searched by the electronic device 100. The address 332A may be extracted from the memo information displayed in the memo display area 332E, indicating the address of the BB Hotel. The selection mark 332F in the memo display area 332E can be used to indicate that the above-mentioned address 332A is the content indicated by the selection mark 332F. The search information source 332B can be used to indicate the source of the searched information (i.e., the address 332A). For example, the search information source 332B is Figure 3C The “memo” shown may indicate that the address 332A is searched from a memo application.

[0150] The navigation control 332C may be used to navigate to the address 332A. In response to the operation of the navigation control 332C, the electronic device 100 may open a map application and navigate from the current location of the electronic device 100 to the location of the address 332A.

[0151] Copy control 332D can be used to copy address 332A. In response to an operation on copy control 332D, such as a click operation, electronic device 100 can copy address 332A (i.e., BB Hotel address) to a clipboard. In this way, the user can paste the address of the BB Hotel at a desired location, for example, to send the address of the BB Hotel to other users.

[0152] Not limited to the navigation control 332C and the copy control 332D, the electronic device 100 may also provide more or fewer function controls for using the above-mentioned address 332A.

[0153] Depend on Figure 3C It can be seen that when a user wants to use a certain address information, the user can directly obtain and use the target address by searching for the target address. In this way, the user does not need to open the memo application to find the memo with the address information recorded, and then manually extract the target address from the memo. The above method can facilitate users to quickly obtain the information they want to search for, and improve the user's experience in information search.

[0154] 4. Figure 3D The example shows a scenario in which a user searches for a phone number.

[0155] like Figure 3D As shown, the electronic device 100 may display a user interface 340. The user interface 340 may be in response to the aforementioned Figure 1A The user interface 340 may include a search box 341. The search box 341 may refer to the aforementioned Figure 3A Search box 311 is shown.

[0156] The user may enter "designer phone number" in the search box 341 to search for the designer's phone number. The content in the search box 341 is "designer phone number". The electronic device 100 may determine that the query statement is "designer phone number".

[0157] For example, the electronic device 100 can search for designer business card photos containing the designer's phone number according to the above query statement. The electronic device 100 can display Figure 3DThe search result display box 342 is shown. The search result display box 342 may include a phone number 342A, a search information source 342B, a dial control 342C, a copy control 342D, a picture 342E, and a selection mark 342F. Among them, the picture 342E may be a photo of a designer's business card containing the designer's phone number searched by the electronic device 100. The phone number 342A may be extracted from the picture 342E, for example, the phone number of a designer named "Zhang**". The selection mark 342F on the picture 342E can be used to indicate that the above-mentioned phone number 342A is the content indicated by the selection mark 342F. The search information source 342B can be used to indicate the source of the searched information (i.e., the phone number 342A). For example, the search information source 342B is Figure 3D The “Gallery” shown may indicate that the phone number 342A is searched from a gallery application.

[0158] The dialing control 342C can be used to dial the phone number 342A. In response to the operation of the dialing control 342C, the electronic device 100 can open the dialing application and dial the phone number 342A.

[0159] The copy control 342D can be used to copy the phone number 342A. In response to an operation on the copy control 342D, such as a click operation, the electronic device 100 can copy the phone number 342A (i.e., the phone number of the designer Zhang**) to the clipboard. In this way, the user can paste the above phone number 342A at a desired location, for example, to send the phone number 342A to other users.

[0160] Not limited to the dialing control 342C and the copy control 342D, the electronic device 100 may also provide more or less function controls for using the above-mentioned phone number 342A.

[0161] Depend on Figure 3D It can be seen that when the user wants to use the target user's phone number, the user can directly obtain and use the target user's phone number by searching the target user's phone number. In this way, the user does not need to open the display page of the designer's business card photo and then manually extract the designer's phone number from the designer's business card photo. The above method can facilitate users to quickly obtain the information they want to search for, and improve the user's experience in information search.

[0162] It should be noted that the above Figure 3A to Figure 3D The content entered in the search box shown is merely an exemplary description of the present application and shall not constitute a limitation on the present application.

[0163] Above Figure 3A to Figure 3DThe search box shown may be a search box provided by a global search application. In some embodiments, the search box provided by the global search application may also be displayed on the negative one screen. That is, the electronic device 100 may determine the content entered in the search box on the negative one screen as a query statement, and use the information search method of the present application to provide the user with the searched information and one or more functional controls using the information.

[0164] By the above Figure 3A to Figure 3D As can be seen from the scenario shown, the electronic device 100 can search for the information to be found by the query statement locally on the electronic device 100 and / or in the cloud according to the query statement entered by the user in the search box provided by the global search application. The electronic device 100 can provide the user with the information to be found by the query statement and provide a functional control for using the above information. This can facilitate the user to quickly obtain the information the user wants to search for and improve the user's experience in information search.

[0165] Figure 4A to Figure 4D Schematic diagrams of other information search scenarios are shown as examples.

[0166] like Figure 4A As shown, the electronic device 100 may display a user interface 410. The user interface 410 may be a chat interface of an instant messaging application. The user interface 410 may include a chat record 411 and an input box 413. The input box 413 may be used to input chat content. For example, the content of the chat record 411 may be "Do you remember Li Si's ID number?" In response to the operation of selecting the text 411A in the chat record 411, the electronic device 100 may display Figure 4A The option box 412 shown. The content of the above text 411A may be "Li Si's ID number". The option box 412 may include a search control 412A. Figure 4A As shown, when the search control 412A is operated, such as a click operation, the electronic device 100 may display Figure 4B User interface 420 is shown.

[0167] like Figure 4B As shown, the user interface 420 may include a search box 421 and a search result display area 422. The search box 421 may be provided by a global search application. Figure 4A The selected text 411A is shown. The electronic device 100 can search using the text 411A as a query statement. The search result display area 422 can be used to display the search results. For example, the content searched by the electronic device 100 based on the text 411A may include: a photo of an ID card containing the ID number of Li Si. The electronic device 100 can display the ID card in the search result display area 422. Figure 4BThe ID number 422A, search information source 422B, insert control 422C, copy control 422D, picture 422E, and selection mark 422F are shown. Among them, picture 422E can be a photo of the ID card containing Li Si’s ID number searched by the electronic device 100. The ID number 422A can be extracted from the picture 422E. The selection mark 422F on the picture 422E can indicate that the above-mentioned ID number 422A is selected and extracted from the picture 422E. The search information source 422B can be used to indicate the source of the searched information (i.e., the ID number 422A). For example, the search information source 422B is Figure 4B The “Gallery” shown may indicate that the ID number 422A is searched from the gallery application.

[0168] Insert control 422C can be used to enter ID number 422A into Figure 4A Input box 413 is shown.

[0169] Copy control 422D can be used to copy identification number 422A.

[0170] In some embodiments, in response to the operation of selecting all the text in the chat record 411 (ie, "Do you remember Li Si's ID number?"), the electronic device 100 may also display Figure 4A Option box 412 is shown. Further, in response to the operation of search control 412A, electronic device 100 can search for the selected file "Do you remember Li Si's ID number?" as the query statement. Electronic device 100 can still obtain Figure 4B The search results shown.

[0171] In some embodiments, the user can also modify the content in the search box 421 to change the content to be searched.

[0172] In response to Figure 4B As shown, by operating the search box 421, such as clicking, the electronic device 100 may display Figure 4C The user interface 430 shown. The user interface 530 may include a search box 421, a search result display area 422, and an input keyboard 431. The search box 421 and the search result display area 422 may refer to the introduction of the aforementioned embodiment. The input keyboard 431 is used to input text content. For example, a user may input the content to be searched in the search box 421 through the input keyboard 431.

[0173] For example, Figure 4D As shown, the user changes the content in the input box 421 by Figure 4C The "Li Si's ID number" shown is changed to Figure 4D The electronic device 100 can be used to Figure 4D The content "Li Si's ID card address" in the search box 421 is used as a query statement to search and display Figure 4D The search result display area 432 is shown. The search result display area 432 may include an address 432A, an insert control 432B, a copy control 432C, a picture 422E, and a selection mark 432D. Among them, the picture 422E may be a photo of an ID card containing the ID card address of Li Si searched by the electronic device 100. The address 432A may be the ID card address of Li Si extracted from the picture 422E. The selection mark 432D on the picture 422E may indicate that the above address 432A is selected and extracted from the picture 422E. The insert control 432B may be used to input the address 432A into Figure 4A Input box 413 is shown. Copy control 432C may be used for address 432A.

[0174] The user is not limited to modifying the content in the search box 421 to the above-mentioned "Li Si's ID card address", and the user can also enter other content to be searched in the search box 421, such as bank card number, telephone number, content in the target document, etc.

[0175] By the above Figure 4A to Figure 4D As can be seen from the scenario shown, the information search capability provided by the above-mentioned global search application can also be called by other APPs. Users can select corresponding content in one or more APPs for search, and quickly obtain the information that the user wants to search through the information search capability provided by the above-mentioned global search application. The electronic device 100 can respond to the user's operation of selecting a section of content for search, use the selected content as a query statement, and search the information to be found by the query statement locally and / or in the cloud on the electronic device 100. The electronic device 100 can provide the user with the information to be found by the query statement, and provide functional controls for using the above information. In other words, in addition to calling up the search box of the global search application and entering a query statement in the search box, the user can also select existing content and use the existing content as a query statement for search, without having to manually enter the above-mentioned existing content in the search box. This can simplify the user's operation of searching for information and improve the user's experience of searching for information.

[0176] In addition, after the user selects existing content for search, the user can also modify the query statement used for the search, so as to more accurately search for the content the user wants to search for or modify the content the user wants to search for.

[0177] Figure 5A to Figure 5D Schematic diagrams of other information search scenarios are shown as examples.

[0178] like Figure 5AAs shown, the electronic device 100 may display a user interface 510. The user interface 510 may be a chat interface of an instant messaging application. The user interface 510 may include a chat record 511 and an input box 513. The input box 513 may be used to input chat content. For example, the content of the chat record 511 may be "Do you remember the latest white blood cell value of Li Si?" In response to the operation of selecting the text 511A in the chat record 511, the electronic device 100 may display Figure 5A The option box 512 shown. The content of the above text 511A may be "Li Si's white blood cell value". The option box 512 may include a search control 512A. Figure 5A As shown, when the search control 512A is operated, such as a click operation, the electronic device 100 may display Figure 5B User interface 520 is shown.

[0179] like Figure 5B As shown, the user interface 520 may include a search box 521 and a search result display area 522. The search box 521 may be provided by a global search application. Figure 5A The selected text 511A is shown. The electronic device 100 can search using the text 511A as a query statement. The search result display area 522 can be used to display the search results.

[0180] For example, the electronic device 100 may search for content based on the text 511A including: a photo of a medical examination report containing the white blood cell count of Li Si, and a memo containing the white blood cell count of Li Si. Based on the above searched content, the electronic device 100 may display the search results in the search result display area 522. Figure 5B Search results 523 to 526 are shown.

[0181] Search result 523 may include white blood cell value 523A, search result source 523B, insert control 523C, and copy control 523D. White blood cell value 523A may be used to indicate the white blood cell value of Li Si searched by electronic device 100. Search result source 523B may be used to indicate the source of white blood cell value 523A. For example, search result source 523B may be Figure 5B The gallery shown may indicate that the white blood cell value 523A is searched from the gallery application. The insert control 523C may be used to input the white blood cell value 523A into Figure 5A Input box 513 is shown. Copy control 523D can be used to copy WBC value 523A.

[0182] The search result 524 may include a white blood cell value 524A, a search result source 524B, an insert control 524C, and a copy control 524D. The white blood cell value 524A may be used to indicate the white blood cell value of Li Si that the electronic device 100 has searched for. The search result source 524B may be used to indicate the source of the white blood cell value 524A. For example, the search result source 524B may be Figure 5B The memo shown may indicate that the white blood cell value 524A is searched from the memo application. The insert control 524C may be used to enter the white blood cell value 524A into Figure 5A Input box 513 is shown. Copy control 524D can be used to copy WBC value 524A.

[0183] Search results 525 and 526 can refer to the above introduction to search result 524. It can be seen that the white blood cell values ​​in search results 525 and 526 are all searched by the electronic device 100 from the memo application. In some embodiments, search results 524 to 526 can be searched by the electronic device 100 from different memo documents in the memo application. For example, multiple memo documents in the memo application all record the white blood cell value of Li Si. The electronic device 100 can query these multiple memo documents according to the above query statement, and extract the white blood cell value of Li Si from these multiple memo documents for user use (such as insertion, copying, etc.).

[0184] In some embodiments, the user may query the specific content of the source of each of the above search results.

[0185] For example, in response to Figure 5B As shown in the operation of the search result 523, such as a click operation, the electronic device 100 can display Figure 5C Picture 523E shown. Picture 523E can be a photo of a physical examination report containing the white blood cell count of Li Si that was searched by the electronic device 100. This can make it convenient for the user to view the specific content in the physical examination report photo. It can be seen that the user can expand the specific content of the search result 523 by clicking on the search result 523. Since the search result 523 is expanded, the display position of the search results displayed after the search result 523 (such as the search result 524, etc.) can be moved downward. In some embodiments, in response to an operation of sliding up or down in the search result display area 522, the electronic device 100 can display the search results that are hidden in the search result display area 522 on the screen. For example, in response to an operation of sliding up or down in the search result display area 522 Figure 5C By sliding upward in the search result display area 522, the electronic device 100 can move the expanded specific content of the search result 523 and the search result 524 upward to display other search results (such as Figure 5B European search results 525, search results 526).

[0186] For example, in response to Figure 5C As shown in the operation of the search result 524, such as a click operation, the electronic device 100 can display Figure 5D The memo display area 524E shown in FIG. The memo display area 524E may display the memo information including the white blood cell value of Li Si that is searched by the electronic device 100 . Figure 5B The white blood cell value 524A shown may be from Figure 5D The selected mark 524F in the memo display area 524E may indicate that Figure 5B The white blood cell value 524A shown is the content indicated by the selected mark 524F. This makes it convenient for the user to view the specific content of the memorandum information containing the white blood cell value of Li Si.

[0187] By the above Figure 5A to Figure 5D As can be seen from the scenario shown, when multiple search results are found according to the query statement, the electronic device 100 can provide the multiple search results for the user to use. In addition, the electronic device 100 can also display the specific content of the source of the multiple search results. This makes it convenient for the user to check which of the multiple search results are needed by the user.

[0188] Figure 6A to Figure 6C Schematic diagrams of other information search scenarios are shown as examples.

[0189] like Fig. 6A As shown, the electronic device 100 can display a user interface 610. The user interface 610 can be an interface for sending emails in an email application. The user interface 610 can include recipient information 611, an email subject 612, an attachment adding control 613, a sending control 614, and an email body display area 615. Among them, the recipient information 611 can be used to indicate the name, email address, and other information of the recipient. The email subject 612 can be used to indicate the subject of the email to be sent. The attachment adding control 613 can be used to add an attachment to the email to be sent. The sending control 614 can be used to send the email. The email body display area 615 can display the body content of the email to be sent.

[0190] Exemplarily, the email body display area 615 may contain text 615A. The content of text 615A may be "Annual performance attachment:". After entering text 615A, the user continues to enter a preset symbol 615B in the email body display area 615. The preset symbol 615B may be, for example, " / @". When the above-mentioned preset symbol 615B is detected in the area for entering text and other content, the electronic device 100 may determine part or all of the text entered before the above-mentioned preset symbol 615B as a query statement for search. In a possible implementation, the electronic device 100 may determine one or more sentences of text before the preset symbol 615B as a query statement. For example, the electronic device 100 may divide each sentence of text according to symbols such as a Chinese period "." or an English period ".". Optionally, the electronic device 100 may determine one or more paragraphs of text before the preset symbol 615B as a query statement. For example, the electronic device 100 may divide the paragraphs of text according to line breaks. Alternatively, the electronic device 100 may also determine the entire document content of the page where the preset symbol 615B is located as a query statement. The embodiment of the present application does not limit the implementation method of the electronic device 100 determining the query statement after recognizing the preset symbol 615B.

[0191] Here, the electronic device 100 determines the text 615A input before the preset symbol 615B as a query sentence as an example. The electronic device 100 searches based on the text 615A, and the searched content may include: files recording annual performance. Fig. 6A As shown, the electronic device 100 can display search results 616 and search results 617 based on the searched content. Among them, search result 616 can be used to indicate a file with a file name of "Annualperformance". Search result 617 can be used to indicate a file with a file name of "2019Annualperformance". It can be seen that although the query statement is "Annual performance attachment", the electronic device 100 searches according to the semantics of the query statement and can search for search results that are semantically related to the query statement but expressed with the same or different words. Search result 616 may include an insert control 616A. Insert control 616A can be used to add the above-mentioned file with a file name of "Annualperformance" as an attachment to the email to be sent. Similarly, search result 617 may include an insert control 617A. Insert control 617A can be used to add the above-mentioned file with a file name of "2019Annualperformance" as an attachment to the email to be sent. In response to Fig. 6A As shown, by operating the insert control 616A, such as clicking, the electronic device 100 may display Figure 6B User interface 610 is shown.

[0192] like Figure 6B As shown, when the electronic device 100 adds the file named "Annualperformance" to the email to be sent, the electronic device 100 can display a file identifier 615C in the email body display area 615. The file identifier 615C can be used to indicate that the file named "Annualperformance" has been added to the email to be sent. In some embodiments, in response to an operation on the file identifier 615C, such as a click operation, the electronic device 100 can open the file named "Annualperformance". In addition, when the above file is added to the email to be sent, the electronic device 100 can cancel the display of the file identifier 615C. Fig. 6A The preset symbol 615B and the search results based on the query statement (such as search result 616 and search result 617) are shown.

[0193] Further, after the user adds the file named "Annualperformance" to the email, he can continue to enter text 615D in the email body display area 615. The content of text 615D can be "wherein the increase of biodegradable cleaning product Q1 is:". The user continues to enter a preset symbol 615E after text 615D. The preset symbol can refer to the above Fig. 6A The preset symbol 615B is shown. The electronic device 100 may determine the text 615D input before the preset symbol 615E as a query sentence for searching. The content searched by the electronic device 100 may include: the value of the increase of the biodegradable cleaning product Q1.

[0194] like Figure 6B As shown, the electronic device 100 can display search results 618 and search results 619 according to the searched content. Among them, search result 618 can be used to indicate the preview content of the increase in biodegradable cleaning product Q1 in the searched file. Search result 618 may include an insert control 618A. Insert control 618A can be used to insert the preview content indicated by the above search result 618 in the email body display area 615. Search result 619 can be used to indicate the numerical value (such as 3%) of the increase in biodegradable cleaning product Q1. Search result 619 may include an insert control 619A. Insert control 619A can be used to insert the numerical value indicated by the above search result 619 in the email body display area 615. Optionally, the electronic device 100 can also display the source of the above search results 618 and search results 619. For example, the source of search results 618 and search results 619 can be the above-mentioned file named "Annualperformance".

[0195] In response to Figure 6BFor the operation of the insert control 618A and the insert control 619A, the electronic device 100 may display Figure 6C User interface 610 is shown.

[0196] like Figure 6C As shown, when the electronic device 100 inserts the content indicated by the above search results 618 and the search result 619 into the email to be sent, the electronic device 100 can display text 615F and table 615G in the email body display area 615. Text 615F can be the numerical value of the Q1 increase of the biodegradable cleaning product indicated by the above search result 619. Table 615G can be the preview content of the Q1 increase of the biodegradable cleaning product in the file indicated by the above search result 618. "Annualperformance" is marked in table 615G, which can indicate that the content of table 615G comes from a file named "Annualperformance". In some embodiments, in response to an operation on table 615G, such as a double-click operation, the electronic device 100 can open the file named "Annualperformance" for the user to view and edit. In addition, when the above text 615F and table 615G are added to the email to be sent, the electronic device 100 can cancel the display. Figure 6B The preset symbol 615E and the search results based on the query statement (such as search result 618 and search result 619) are shown.

[0197] Above Fig. 6A and Figure 6B The preset symbol " / @" shown is only an exemplary illustration of the present application and should not be construed as limiting the present application. The content of the above-mentioned preset symbol may also be other. The above-mentioned preset symbol may be a single symbol, for example, " / " or "@" or "#", etc. The above-mentioned preset symbol may also be a combination symbol, for example, " / #" or "@#", etc. Not limited to the above-mentioned preset symbols, the electronic device 100 may also determine the query statement for search when other preset operations are detected. For example, the above-mentioned preset operation may be an operation of a preset shortcut key. In response to the operation of the above-mentioned preset shortcut key, the electronic device 100 may determine the query statement (such as one or more sentences of text before the input focus, etc.) according to the position of the input focus in the input box and search for it.

[0198] In a possible implementation, the electronic device 100 may search for content that matches the semantics of the query statement in the file inserted before detecting the preset symbol. Figure 6A to Figure 6C It can be seen that the electronic device 100 detects Figure 6BThe preset symbol 615E shown previously inserted a file named "Annualperformance" into the email. The semantics of the query statement (i.e., text 615D) is that in the file named "Annualperformance", the biodegradable cleaning product Q1 increased. Figure 6B The preset symbol 615E shown in the figure, the electronic device 100 can preferentially search for the content with the semantic matching of the text 615D in the file named "Annualperformance", thereby finding Figure 6B Search results 618 and search results 619 are shown.

[0199] That is, the electronic device 100 can narrow the search scope according to the context information of the query statement. This can improve the efficiency of information search and save power consumption of information search. The electronic device 100 can search for the information to be searched by the query statement more quickly.

[0200] By the above Figure 6A to Figure 6C As can be seen from the scenario shown, the information search capability provided by the global search application can also be called by other apps. After the user enters text that can be used as a query statement in the text editing scenario, the user can call the information search capability provided by the global search application by entering a preset symbol or performing other preset operations, so as to quickly insert the information they want to search in the text editing box. The above embodiment can facilitate users to quickly obtain the information they want to search for and improve the user experience of text editing.

[0201] Figure 7A to Figure 7G Schematic diagrams of other information search scenarios are shown as examples.

[0202] like Fig. 7A As shown, the electronic device 100 may display a user interface 710. The user interface 710 may be an interface of a text editing application, such as a memo application. The user interface 710 may include text 711 input by the user. For example, the content of the text 711 may be "The screen resolution of the new mobile phone under development is:". The electronic device 100 may display a text message 711 at the end of the text input by the user. Fig. 7A The query control 712 is shown. In response to Fig. 7A The operation of the query control 712, such as a click operation, can determine part or all of the text previously input into the query control 712 as a query statement for search. The method for determining the query statement in response to the operation of the query control 712 by the electronic device 100 can refer to the aforementioned Fig. 6A The method in which the electronic device 100 determines the query statement after the detected preset symbol 615B is not described here.

[0203] Here, the electronic device 100 determines the text 711 input before the query control 712 as a query sentence as an example. The electronic device 100 can search according to the text 711.

[0204] In some embodiments, the electronic device 100 may display the Figure 7B The prompt box 713 shown. The prompt box 713 may include a prompt content "Searching for related documents", which can be used to prompt the user that the electronic device 100 is searching. Further, when a file containing the information to be searched by the query statement (i.e., text 711) is found, the electronic device 100 may display Figure 7C The prompt box 714 shown. The prompt box 714 may include the prompt content "The document "Next Generation Mobile Phone Hardware Specifications" has been found, and the specific content is being searched from the document", which can be used to prompt the user that the relevant file has been found and the information to be searched by the query statement is being extracted from the relevant file. For example, the document "Next Generation Mobile Phone Hardware Specifications" mentioned in the above prompt content can be a file searched by the electronic device 100 that contains the information to be searched by the query statement (i.e., text 711). When the information to be searched by the query statement is extracted from the above relevant files, the electronic device 100 can display Fig.7D Search result 715D is shown.

[0205] like Fig.7D As shown, search result 715D may include resolution 715A, insert control 715B, file content 715C, and search result source 715D. Resolution 715A may be used to indicate the new mobile phone screen resolution searched by electronic device 100. Insert control 715B may be used to insert resolution 715A after text 711. File content 715C may include the context of resolution 715A. Search result source 715D may be used to indicate the source of resolution 715A. For example, search result source 715D may be Fig.7D The “from Next Generation Mobile Phone Hardware Specifications” shown may indicate that the resolution 715A is searched from the document Next Generation Mobile Phone Hardware Specifications. The above file content 715C and search result source 715D may facilitate the user to determine whether the resolution 715A searched and extracted by the electronic device 100 is the mobile phone screen resolution that the user wants to search for.

[0206] In response to Fig.7D As shown in the operation of inserting control 715B, such as clicking operation, electronic device 100 can display Fig. 7E User interface 710 is shown.

[0207] like Fig. 7EAs shown, the electronic device 100 inserts text 716 after the text 711 and displays the query control 712 after the text 716. The text 716 is the aforementioned Fig.7D Resolution 715A shown.

[0208] Above Figure 7B The prompt box 713 and Figure 7C The prompt box 714 shown is optional. In some embodiments, in response to Fig. 7A The operation of the query control 712 is shown, and the electronic device 100 can directly display the query after searching for the information to be searched by the query statement. Fig.7D The search results 715 are shown without displaying Figure 7B The prompt box 713 and Figure 7C Prompt box 714 is shown.

[0209] In some embodiments, in response to Fig.7D The electronic device 100 can also insert a text after the text 711 by operating the insert control 715B. Figure 7F The text 717 shown. The display style of the text 717 can be used to prompt the user that the text 717 supports user interaction. The display style of the text 717 may include: the color of the text 717 is different from the color of the text 711, the text 717 is underlined, etc. The embodiment of the present application does not limit the display style of the text 717. For example, in response to a click operation on the text 717, the electronic device 100 may display Figure 7G The prompt box 718 shown. The prompt box 718 can be used to display the source of the inserted text 717. The content in the prompt box 718 can refer to the aforementioned Fig.7D The electronic device 100 can also collapse the prompt box 718 in response to an operation of clicking the text 717 again, or an operation of clicking a blank area of ​​the user interface 710. The operation for collapsing the prompt box 718 is not limited in the embodiment of the present application.

[0210] In some embodiments, the query control 712 may be provided by the electronic device 100 in response to a preset operation. For example, when an operation for a preset shortcut key is detected, or in response to inputting the aforementioned Figure 6A to Figure 6C The electronic device 100 can display the preset symbol operation. Fig. 7A The electronic device 100 may cancel the display of the query control 712 after detecting an operation (such as a click operation) on the query control 712. In other words, Figure 7B to Figure 7G The user interface shown may not include a query control. The embodiment of the present application does not limit the operation for calling the query control 712.

[0211] By the above Figure 7A to Figure 7E As can be seen from the scenario shown, the information search capability provided by the global search application can also be called by other APPs. The electronic device 100 can provide a query control in the text editing scenario (refer to Fig. 7A The query control 712B shown in the figure is used to allow the user to quickly search for the text entered before the query control. The above embodiment can facilitate the user to quickly obtain the information the user wants to search for, and improve the user's experience in text editing.

[0212] Figure 8A to Figure 8E Schematic diagrams of other information search scenarios are shown as examples.

[0213] like Fig. 8A As shown, the electronic device 100 can display a user interface 810. The user interface 810 can be an interface for entering information (such as an interface for filling in registration information). The user interface 810 can include multiple input boxes: a name input box 811, a mobile phone number input box 812, an ID number input box 813, a school input box 814, and a major input box 815. Among them, the name input box 811 can be used to enter the user's name. The mobile phone number input box 812 can be used to enter a mobile phone number. The ID number input box 813 can be used to enter an ID number. The school input box 814 can be used to enter the school name. The major input box 815 can be used to enter the major name.

[0214] In some embodiments, when an operation to wake up the voice assistant is detected, the electronic device 100 may display Figure 8B User interface 820 shown. User interface 820 can be an interface for a user to communicate with the electronic device 100 through a voice assistant to instruct the electronic device 100 to execute a corresponding voice command. The operation of waking up the voice assistant can be, for example, an operation of waking up by a wake-up word, an operation of pressing a preset button, and so on. The embodiment of the present application does not limit the operation for waking up the voice assistant. The voice assistant can be an application that enables a user to interact with the electronic device 100 using natural language and control the electronic device 100 to execute voice commands through technical means such as speech recognition, speech synthesis, and semantic analysis. The voice assistant can also be called other names, such as a smart assistant, shortcut commands, and so on.

[0215] Alternatively, the user interface 820 may be a user interface of an artificial intelligence chat application. The artificial intelligence chat application may be an APP that uses an artificial intelligence model such as a language model to understand and generate natural language. Based on the artificial intelligence chat application, the electronic device 100 may respond to user input and give corresponding feedback. The user input may include, but is not limited to: content manually entered by the user through the input keyboard, voice commands spoken by the user, and the like. The feedback given by the electronic device 100 may include, but is not limited to: querying and providing information related to the user input, performing corresponding tasks according to the user input, and the like. The artificial intelligence chat application may also be referred to as a virtual assistant, a personal assistant, and the like.

[0216] The application to which the above user interface 820 belongs is only an exemplary description of the present application. The present embodiment of the application does not limit the operation method for triggering the electronic device 100 to display the user interface 820.

[0217] like Figure 8B As shown, the user interface 820 may include a dialog box 822. The dialog box 822 may include information 823. The information 823 may be used to instruct the user to input the user's needs to the electronic device 100. For example, the content of the information 823 may include "May I ask what help I need?" The dialog box 822 may also include an input box 824. The input box 824 may be used for the user to input, so that the user can ask questions or give instructions to the electronic device 100. In some embodiments, in addition to displaying the above information 823 on the screen, the electronic device 100 may also voice broadcast the content of the above information 823.

[0218] like Figure 8C As shown, the electronic device 100 can receive user input and display information 825 in the dialog box 822 according to the user input. Information 825 can be input by user voice, or can be manually input by the user through the input keyboard. The embodiment of the present application does not limit the input method of information 825. For example, the content of information 825 can be "I just saved a screenshot in the chat application." The electronic device 100 can search for a screenshot recently saved in the chat application in the gallery application according to information 825, and display it. Figure 8C The information 826 and the picture 827 shown are shown. The information 826 can be used to prompt the user to confirm whether the picture searched by the electronic device 100 is the picture the user wants to find. For example, the content of the information 826 can be "Is it this screenshot?". The picture 827 can be the picture searched by the electronic device 100 according to the information 825.

[0219] like Fig.8DAs shown, the user can enter information 824A in the input box 824 and send the information 824A to the dialog box 822 through the send control in the input box 824. For example, the content of the information 824A can be "Yes, help me fill in the information in the picture into the registration form." It can be seen that the information 824A includes instructions for instructing the electronic device 100 to recognize the information in the picture 827 and fill the information into the registration form.

[0220] When the electronic device 100 sends the information 824A to the dialog box 822, the electronic device 100 can identify the information 824A and determine that the picture indicated in the information 824A is Fig.8D As shown in picture 827, the registration form is Fig. 8A An enrollment form in user interface 810 is shown.

[0221] In a possible implementation, the electronic device 100 may obtain description information of each input box in the registration form. The description information of an input box may be used to indicate information about the content to be input in the input box. The description information of the input box may be obtained by the electronic device 100 based on the code written on the page where the registration form is located, or may be obtained by the electronic device 100 performing image recognition on the image of the registration form. The present application does not limit the method by which the electronic device 100 obtains the description information of the input box.

[0222] For example, the electronic device 100 may obtain Fig. 8A The description information of the input box 811 shown includes "name", the description information of the input box 812 includes "mobile phone number", the description information of the input box 813 includes "ID number", the description information of the input box 814 includes "school name", and the description information of the input box 815 includes "major name".

[0223] Furthermore, the electronic device 100 may determine the description information of each input box in the registration form as a query statement, and search for corresponding information from the image 827 according to the semantics of the query statement, thereby filling the searched information into the input box associated with the query statement.

[0224] For example, the electronic device 100 may determine the description information (i.e., "name") of the input box 811 as a query statement. The electronic device 100 may query the information whose content is the name from the picture 827, and obtain the text "Zhang San". The electronic device 100 may fill the text "Zhang San" into the input box 811. For another example, the electronic device 100 may determine the description information (i.e., "mobile phone number") of the input box 812 as a query statement. The electronic device 100 may query the information whose content is "mobile phone number" from the picture 827, and obtain the text "188********". The electronic device 100 may fill the text "188********" into the input box 812. The electronic device 100 may Fig. 8A The description information of other input boxes in the user interface 810 is determined as a query statement, and the process of searching for information in the picture 827 can refer to the above description of the input box 811 and the input box 812. No further description will be given here.

[0225] like Fig. 8E As shown, the electronic device 100 can select the input box from the user interface 810 according to the description information of each input box in the registration form. Fig.8D The name (i.e., "Zhang San"), mobile phone number (i.e., "188********"), ID number (i.e., "123***"), school name (i.e., "XX University"), and major name (i.e., "Communication Engineering") are extracted from the picture 827 shown. The electronic device 100 can fill these extracted information into the corresponding input boxes respectively. It can be seen that even if there are multiple pieces of information in the picture that are not convenient to copy and paste directly, the above embodiment can also facilitate the user to instruct the electronic device 100 to extract these multiple pieces of information and fill them into the corresponding target area. The user does not need to manually perform multiple text recognition and copy operations on the picture, and then repeatedly switch between the image display interface and the registration display interface to paste the multiple pieces of information in the input box in turn.

[0226] The electronic device 100 is not limited to searching for information from the above-mentioned pictures and filling the information into the target area. The electronic device 100 can also search for information from files of the same type as text files, table files, etc. and fill the information into the target area.

[0227] By the above Figure 8A to Figure 8E As can be seen from the scenario shown, in combination with the voice assistant and / or language model, the electronic device 100 can recognize the user's instructions, extract information from the specified file and fill it into the target area. In this way, when the information in the specified file needs to be filled into the target area, the user can directly issue a search and fill instruction to the electronic device 100 without manually copying and pasting. The above method simplifies the user's operations of searching, obtaining and filling in information, and improves the efficiency of the user in obtaining information.

[0228] It should be noted that the above information search scenarios exemplify some of the information search entrances provided by this application. For example, Figure 3A to Figure 3B The search box 311 shown, Figure 4A The search control 412A shown, Fig. 6A The preset symbol 615B shown, Fig. 7A The query control 712 shown, Figure 8B to Figure 8D Dialog box 822 is shown. Not limited to the above-mentioned information search entrances, the electronic device 100 can also provide more information search entrances for the user to quickly search and obtain the information they want to search.

[0229] The following describes the information search method provided by this application in conjunction with the above information search scenario.

[0230] The information search method provided in the present application is implemented based on a semantic vector database. In some embodiments, a semantic vector database may be stored in the electronic device 100. The semantic vector database may store semantic vectors associated with files locally in the electronic device 100 and / or in the cloud. Among them, a file may be associated with one or more semantic vectors.

[0231] Before introducing the information search method, here we first introduce the method of establishing a semantic vector database.

[0232] Fig. 9 The flowchart of the method for the electronic device 100 to establish a semantic vector database is exemplified.

[0233] S911. Obtain files locally and / or in the cloud of the electronic device 100, where the files include pictures, text files, spreadsheet files, or audio and video files.

[0234] The above-mentioned text file may refer to a file whose file content includes text. The above-mentioned table file may refer to a file whose file content includes a table. The above-mentioned audio and video file may include an audio file and a video file. This application does not limit the type of file obtained by the above-mentioned electronic device 100.

[0235] S912. Extract semantic vectors from the acquired files using a semantic vector extraction model, and store the extracted semantic vectors in a semantic vector database. The semantic vector database contains semantic vectors associated with each file. One file is associated with one or more semantic vectors.

[0236] The above-mentioned semantic vector extraction model can be used to extract the semantic vector of given content. The above-mentioned given content can be data including but not limited to text, table, picture and other types. The semantic vector extraction model can be a model based on a neural network. The embodiment of the present application does not limit the implementation method of the semantic vector extraction model. The electronic device 100 inputs a section of content into the semantic vector extraction model, and the semantic vector of this section of content can be obtained through the semantic vector extraction model. The semantic vector of this section of content can represent the semantics of this section of content. For example, the semantics of this section of content can include an overview of the information described by this section of content (the theme or main idea of ​​this section of content).

[0237] For example, the electronic device 100 inputs a text about cats into the semantic vector extraction model, and the semantic vector of the text can be used to indicate that the text is a text about cats. The electronic device 100 inputs a photo of a person taken at an amusement park into the semantic vector extraction model, and the semantic vector of the photo can be used to indicate that the photo is a photo of a person taken at an amusement park. The electronic device 100 inputs a photo of Zhang San's ID card into the semantic vector extraction model, and the semantic vector of the photo can be used to indicate that the photo is a photo of Zhang San's ID card.

[0238] In some embodiments, a file may contain multiple contents (or multiple data fragments). The electronic device 100 may split the contents in a file and determine the semantic vectors associated with each data fragment after the split. In this way, a file may be associated with multiple semantic vectors. For example, a text file may contain multiple paragraphs of text. The electronic device 100 may split the text file according to paragraphs, and extract the semantic vector associated with each paragraph through a semantic vector extraction model. Alternatively, a text file may contain multiple chapters. The electronic device 100 may split the text file according to chapters, and extract the semantic vector associated with each chapter through a semantic vector extraction model. For another example, a table file may contain multiple rows of data. The electronic device 100 may split the table file by row, and extract the semantic vector associated with each row of data in the table file through a semantic vector extraction model. For another example, a presentation document may contain multiple pages of data. The electronic device 100 may split the presentation file by page, and extract the semantic vector associated with each page of data in the presentation document through a semantic vector extraction model.

[0239] It is understandable that the themes to be expressed in different paragraphs or chapters in a text file may be different. For example, the first paragraph of a text file introduces the types of cats, and the second paragraph introduces the living habits of cats. The information to be expressed by data in different rows of a table file may also be different. For example, the first row of a table file records the sales volume of product 1, and the second row records the sales volume of product 2. The themes to be expressed by the contents of different pages in a presentation document may also be different. For example, the first page of a presentation document introduces the background technology of the solution, and the second page introduces the specific implementation method of the solution. The above-mentioned splitting of the file and then extracting the semantic vectors of the split data segments can facilitate the electronic device 100 to more accurately find the information that the user wants to search for when searching for information.

[0240] The present application embodiment does not limit the granularity of the above-mentioned split file. For example, the granularity of splitting the file may include but is not limited to: by text sentence, by text paragraph, by text chapter, by file page, by table row, by table column, etc.

[0241] Optionally, the electronic device 100 may also treat a file as a whole and extract a semantic vector associated with the file through a semantic vector extraction model, that is, a file may be associated with a semantic vector.

[0242] In some embodiments, the semantic vector database may also be established by a cloud server. After establishing the semantic vector database, the cloud server may send the semantic vector database to the electronic device 100. Optionally, the semantic vector database may also be stored in the cloud server.

[0243] In some embodiments, when the files stored locally on the electronic device 100 change, or when the files stored in the cloud storage space associated with the electronic device 100 change, the electronic device 100 can update the semantic vector database. The file changes may include but are not limited to: newly added files, changes in the content of the files, deletion of existing files, etc.

[0244] Fig.10 The flowchart of the information search method provided by the present application is exemplified.

[0245] like Fig.10 As shown, the information search method may include steps S1011 to S1015.

[0246] S1011. Obtain a query statement.

[0247] The electronic device 100 may obtain a query statement. The query statement may indicate content for instructing the electronic device 100 to search. In some embodiments, the electronic device 100 may obtain a query statement based on content entered in a search box. The search box may be, for example, a search box provided by a global search application. For details, please refer to the aforementioned Figure 3A to Figure 3D In other embodiments, the electronic device 100 can obtain a query statement based on the user's operation of selecting a piece of content and searching. Figure 4A and Figure 4B In other embodiments, the electronic device 100 may obtain a query statement based on a preset symbol detected in the input box or based on a detected operation on a shortcut key. Figure 6A to Figure 6C In other embodiments, the electronic device 100 may obtain a query statement based on an operation on a query control detected in the input box. Figure 7A to Figure 7D In other embodiments, the electronic device 100 can obtain the query statement according to the description information of the input box to be filled in. Figure 8A to Figure 8E The embodiment of the present application does not limit the method for the electronic device 100 to obtain the query statement.

[0248] S1012. Determine file content information and file attribute information from the query statement through a language model. The file content information may represent the content described by the file containing the information to be queried by the query statement. The file attribute information may represent one or more attribute information such as the creation time, creation location, creation user, and the APP to which the file containing the information to be queried by the query statement.

[0249] The language model may refer to an artificial intelligence (AI) model for processing language (or symbol system), which can be used to generate text that meets the requirements according to the prompt information (prompt), and ensure that the output result is related to the prompt. The language model may include a language model based on probability theory and statistics (i.e., a statistical language model), a language model based on deep learning and neural network implementation (i.e., a neural network language model), and the like. The embodiment of the present application does not limit the implementation method of the language model. Exemplarily, the electronic device 100 may implement the information search method of the present application through a large language model (LLM). Among them, LLM may be a neural network model that can learn the grammar and semantics of natural language to generate human-readable text. Among them, LLM may be obtained by training using a large-scale corpus. The above-mentioned corpus may include a large amount of text data. LLM can handle various natural language processing tasks, such as natural language generation, text error correction, text classification, text summarization, machine translation, speech recognition, and the like.

[0250] Among them, the above prompt can be a natural language that humans can understand (i.e., a hard prompt (hard prompt / discrete prompt)). For example, the prompt can be a text or sentence composed of natural language. Alternatively, the prompt can be machine-readable content, which belongs to a non-natural language (i.e., a soft prompt (soft prompt / continuous prompt)). For example, a soft prompt can be an embedding, which is a word converted into a meaning vector representation processed by a computer. Hard prompts are more interpretable. Soft prompts can more flexibly eliminate the parameter restrictions of the language model. Prompt can be used to start and guide the language model to generate output of a specified type, theme or format. Exemplarily, in the field of natural language processing, a prompt can include a set of questions and answers or task descriptions. For example, the prompt is: "Give your pet three names", "Translate this English sentence into French", etc. For another example, the prompt can also include question and answer examples. The prompt for the task description "Give your pet three names" may include question-and-answer examples: "Pet type: cat, pet name: name 1, name 2, name 3", "Pet type: dog, pet name: name 4, name 5, name 6". It can be understood that the question-and-answer examples included in the above prompt can be used to guide the language model to answer the user's questions in the manner of the question-and-answer examples. The language model can generate text that meets the requirements based on the prompt and ensure that the output result is related to the prompt.

[0251] In some embodiments, the above-mentioned language model may be deployed in a cloud server. The electronic device 100 may send a query statement to the cloud server. Then, the cloud server may determine the file content information and the file attribute information from the query statement through the language model. The cloud server may send the file content information and the file attribute information to the electronic device 100. In other embodiments, the electronic device 100 may store a language model. When the query statement is obtained, the electronic device 100 may determine the file content information and the file attribute information from the query statement through the language model.

[0252] The above-mentioned file content information determined by the query statement may represent the semantic limitation of the information to be searched by the query statement in the query statement. In other words, the file content information may be a condition that limits the semantics or meaning of the search results, and may be used by the electronic device 100 to search for the search results required by the query statement according to the semantics. The above-mentioned file attribute information determined by the query statement may represent the attribute limitation of the information to be searched by the query statement in the query statement. The embodiment of the present application does not limit the content contained in the file attribute information. For example, the file attribute information may include one or more of the following: creation time, creation location, creation user, APP to which it belongs, modification time, number of modifications, file size, storage location, etc. In other words, the file content information may be a condition that limits the attributes of the file to which the search results belong, and may be used by the electronic device 100 to search for the file to which the search results required by the query statement belong according to the attributes, so that the search results can be extracted from the file.

[0253] The electronic device 100 can search for relevant files according to the file content information and file attribute information determined by the query statement, and extract the content to be searched by the query statement from the relevant files.

[0254] The file content information of a file can be determined from the content described by this file. The file content information of a file can represent the semantics of this file or part of the content in this file. The file attribute information of a file may include one or more attribute information of this file, for example, creation time, creation location, creation user, belonging APP, modification time, modification times, file size, storage location, etc. In some embodiments, the electronic device 100 can use a file system to obtain the attribute information of each file. Among them, the file system can be a method and data result used by the operating system to clarify the files on the disk or partition, which can be used to manage the files stored in the electronic device 100. When storing a file, in addition to storing the actual content of the file (such as the text content recorded in a text file, the pixel data contained in a picture file, etc.), the file system also stores the attribute information of the file. Optionally, the electronic device 100 can also obtain the attribute information of the file through file data. Among them, the file data of a file stored in the electronic device 100 includes not only the actual content of the file, but also the descriptive information of the file. These descriptive information are also the attribute information of the file. When opening a file, the electronic device can read the actual content of the file from the file data and display it on the screen. The types of attribute information may be different in the file data of files of different formats. For example, the file data of a picture file may contain the attribute information "resolution" but not the attribute information "number of paragraphs". The file data of a text file may contain the attribute information "number of paragraphs" but not the attribute information "resolution". Optionally, the electronic device 100 may also obtain the attribute information of a file from the application based on the internal information of the application. Wherein, the electronic device 100 may obtain the internal information of the application if the application is authorized. For example, the electronic device 100 may access the chat history in a chat application, determine who sent the file in the chat history, and thereby determine the attribute information "sender" of the file. The embodiment of the present application does not limit the method by which the electronic device 100 determines the file attribute information of a file.

[0255] It is understandable that the file content information of a file can be viewed after opening the file. The file attribute information of a file can be displayed in response to an operation of viewing file attributes. The above-mentioned operation of viewing file attributes can be, for example, an operation on a property control after right-clicking the mouse when the cursor is placed at the location of the file shortcut.

[0256] In some embodiments, the file attribute information of a file may not be included in the content described in the file. For example, the file content information corresponding to a photo of a dog walking by the river may include the river, the person walking the dog, and the dog. However, the photo of the dog walking by the river does not include the time when the photo was taken. The camera application of the electronic device 100 will record the shooting time when taking the photo of the dog walking by the river. Therefore, the file attribute information corresponding to the photo may include the shooting time.

[0257] Here, a method for determining file content information and file attribute information from a query statement using a language model is exemplified.

[0258] The input of the language model may include a query statement, prompt1 and prompt2. Among them, prompt1 can be used to instruct the language model to determine the file content information from the query statement. For example, prompt1 can be: Please generalize the given content, anonymize the specific time, place, name, file size, and be as concise as possible while maintaining the meaning of the given content description. prompt2 can be used to instruct the language model to determine the file attribute information from the query statement. For example, prompt2 can be: If there is time, place, name, file size, and file type in the given content, please extract this information from the given content. Among them, the time, place, and name used to instruct the language model to extract in prompt2 can respectively represent the creation time (or shooting time, or sending time, or receiving time) of the file, the creation location (or shooting location), and the creation user (or sending user, or receiving user).

[0259] Exemplarily, the query statement is "technical documents sent by Zhang San yesterday". The file content information output by the language model according to prompt1 may include: technical documents. The file attribute information output by the language model according to prompt2 may include: Zhang San, yesterday. In this way, based on the above file content information and file attribute information, the electronic device 100 can search for files sent by a user named "Zhang San" yesterday in all files in the local and / or cloud of the electronic device 100, and find files with the content of technical documents from the files sent by Zhang San yesterday. For another example, the query statement is "photos of walking the dog by the river taken in March last year". The file content information output by the language model according to prompt1 may include: walking the dog by the river in spring. The file attribute information output by the language model according to prompt2 may include: March last year, photos. In this way, based on the above file content information and file attribute information, the electronic device 100 can search for photos taken in March last year in all pictures in the local and / or cloud of the electronic device 100, and find photos with the content of walking the dog by the river in spring from the photos taken in March last year. Among them, the shooting time of the above photos can be recorded by the electronic device 100 when taking the photos. It can be seen that the term "last March" in the query "photos of walking the dog by the river taken last March" can be used to limit the shooting date of the photo and the season presented by the photo content. For example, if the photo content contains elements such as tender shoots and flowers, it can be said that the season presented by the photo content is spring. If the photo content contains elements such as the scorching sun, it can be said that the season presented by the photo content is summer. If the photo content contains elements such as withered yellow leaves, it can be said that the season presented by the photo content is autumn. Therefore, the term "last March" in the above query can be used to determine file content information (such as "spring") and file attribute information (such as "last March"). That is to say, a word, a sentence or a text in the query may contain both the limitation of file attribute information and the limitation of file content information. The language model can extract all possible limitation conditions for file content and file attributes from the query.

[0260] In some embodiments, the query statement may not contain file attribute information such as time, location, name, file size, etc. The content obtained by the language model may not contain file attribute information. In the case where the query statement does not contain file attribute information, the electronic device 100 can also search for the information to be searched by the query statement based on the file content information.

[0261] For example, the query statement is "ID number". The file content information output by the language model according to prompt1 may include: ID number. Since the query statement does not include file attribute information, the file attribute information output by the language model according to prompt2 may be empty.

[0262] In some other embodiments, the query statement may only include file attribute information but not file content information. For example, the query statement is "photos sent by Zhang San". The file attribute information output by the language model according to prompt2 may include: Zhang San, photos. The file content information output by the language model according to prompt1 may be empty.

[0263] S1013. Use the file content information as input of the semantic vector extraction model to determine the semantic vector 1 of the query statement. The semantic vector 1 can represent the semantics of the query statement.

[0264] The semantic vector extraction model can refer to the above Fig. 9 Shown is the introduction of S912.

[0265] S1014. Search for one or more files from the files locally on the electronic device 100 and / or in the cloud based on the file attribute information, and then search for the semantic vector 2 that is most similar to the semantic vector 1 from the semantic vectors associated with the one or more files in the semantic vector database based on the semantic vector 1.

[0266] The file attribute information can indicate the source of the file. The electronic device 100 can search for the file indicated by the file attribute information locally on the electronic device 100 and / or in the cloud based on the file attribute information. Fig. 9 It can be known that a semantic vector database may be stored in the electronic device 100. The semantic vector database may store semantic vectors associated with one or more files found by the electronic device 100.

[0267] Since a file may be associated with multiple semantic vectors, the electronic device 100 may calculate vector similarity to determine the semantic vector that is most similar to the semantic vector 1 among the semantic vectors associated with one or more files found by the electronic device 100 .

[0268] The embodiment of the present application does not limit the method for calculating vector similarity by the electronic device 100. For example, the electronic device 100 may use methods such as cosine similarity, Euclidean distance, or Pearson correlation coefficient to calculate the similarity between semantic vectors, thereby finding the semantic vector most similar to semantic vector 1.

[0269] In some embodiments, after the electronic device 100 calculates the similarity between the semantic vectors associated with the above one or more files and the semantic vector 1, it can first filter out the semantic vectors whose similarity with the semantic vector 1 is higher than the similarity threshold. The electronic device 100 can determine one or more semantic vectors with the highest similarity among the semantic vectors whose similarity is higher than the similarity threshold as the semantic vector most similar to the semantic vector 1. The above similarity threshold can be preset, and the present application does not limit the value of the similarity threshold. For example, when using cosine similarity to calculate the similarity, the above similarity threshold can be 0.8, 0.85, etc.

[0270] Among them, if the similarity between the semantic vectors associated with the above one or more files and the semantic vector 1 is lower than the similarity threshold, the electronic device 100 can prompt the user that no relevant information has been searched. It can be understood that the similarity between the semantic vectors associated with the above one or more files and the semantic vector 1 is lower than the similarity threshold, which can indicate that the one or more files do not contain the information to be searched by the query statement.

[0271] Here, the semantic vector 2 is taken as an example to be the most similar semantic vector to the semantic vector 1.

[0272] S1015, determining data 1 associated with semantic vector 2, taking data 1 and a query statement as inputs of a language model, and extracting information to be queried by the query statement from data 1 through the language model.

[0273] The above data 1 may be a data segment in a file, or may be all the data in a file.

[0274] In addition to the above data 1 and query statements, the input of the language model may also include prompt information prompt3. Prompt3 may be used to instruct the language model to extract the information to be queried by the query statement from input 1. For example, prompt3 may be: answer the question of the query statement as truthfully as possible based on the provided data 1. If the answer content is not in the provided data 1, please answer "I don't know". The content of prompt3 above is only an exemplary description of the present application and shall not constitute a limitation on the present application.

[0275] In some embodiments, the electronic device 100 may display the information to be queried by the query statement extracted from the data 1 on the screen for the user to use. Optionally, the electronic device 100 may also determine the purpose of the information to be queried by the query statement and provide corresponding function controls on the screen so that the user can more conveniently use the information to be queried by the query statement.

[0276] If the output of the language model is “I don’t know”, the electronic device 100 may prompt the user that no relevant information has been searched.

[0277] It should be noted that the above step S1012 is optional. When a query statement is obtained, the electronic device 100 can use the query statement as input to the semantic vector extraction model to obtain the semantic vector of the query statement, and then perform the above steps S1014 and S1015 to obtain the information to be queried by the query statement.

[0278] In the above step S1015, extracting the information to be queried by the query statement from the input 1 through the language model is also optional. For example, when the information to be queried by the query statement is the file itself, the electronic device 100 can provide the data 1 to the user after determining the data 1 associated with the semantic vector 2 (the data 1 is the entire file). In some embodiments, the electronic device 100 providing the data 1 to the user can specifically mean that the electronic device 100 provides the file itself as an option to the user (refer to Fig. 6A Search results 616 and 617 are shown).

[0279] For example, the electronic device 100 may obtain the aforementioned Figure 3A The query sentence "Zhang San's ID card number" is shown. The file content information output by the language model according to prompt1 in the above step S1012 may include: ID card number. The file attribute information output by the language model according to prompt2 in the above step S1012 may include: Zhang San. In some embodiments, according to the above file attribute information, the electronic device 100 may use an inverted index or other methods to search for files containing the text "Zhang San". The above inverted index can be used to quickly obtain a list of files containing this text based on the text. The above file containing the text "Zhang San" may include a photo of Zhang San's ID card. The electronic device 100 may input the above file content information into a semantic vector extraction model to determine the semantic vector of the query sentence. For example, the semantic vector of the query sentence "Zhang San's ID card number" can be used to indicate that the semantics of the query sentence is: ID card number. The electronic device 100 can search for the semantic vectors associated with the above file containing the text "Zhang San" from the semantic vector database, and find the semantic vector that is most similar to the semantic vector of the query sentence from these semantic vectors. For example, the semantic vector that the electronic device 100 finds to be most similar to the semantic vector of the query sentence may be a semantic vector representing ID card information. The electronic device 100 can determine the data associated with the most similar semantic vector, namely, the ID card photo of Zhang San. The electronic device 100 inputs the ID card photo of Zhang San and the query sentence "Zhang San ID card number" into the language model, and can extract the ID card number from the ID card photo of Zhang San through the language model (refer to Figure 3A ID number 312A shown).

[0280] For another example, the electronic device 100 may obtain the aforementioned Figure 5AFor the query sentence "Li Si's recent white blood cell value" shown in the figure, the file content information input by the language model according to prompt1 in the above step S1012 may include: white blood cell value. The file attribute information input by the language model according to prompt2 in the above step S1012 may include: Li Si, recent. In some embodiments, according to the above file attribute information, the electronic device 100 may search for a file containing the text "Li Si". The above file containing the text "Li Si" may include a photo of Li Si's physical examination report, a memo information recording Li Si's physical examination results, and the like. The electronic device 100 may input the above file content information into the semantic vector extraction model to determine the semantic vector of the query sentence. For example, the semantic vector of the query sentence "Li Si's recent white blood cell value" may be used to indicate that the semantics of the query sentence is: white blood cell value. The electronic device 100 may search for the semantic vectors associated with the above file containing the text "Li Si" from the semantic vector database, and find the semantic vector that is most similar to the semantic vector of the query sentence from these semantic vectors. For example, the semantic vector that the electronic device 100 finds to be most similar to the query sentence may include a semantic vector representing physical examination information. The electronic device 100 can determine the data associated with the most similar semantic vector, namely, the photo of Li Si's physical examination report and the memo information recording Li Si's physical examination results. The electronic device 100 inputs the photo of Li Si's physical examination report and the query sentence "Li Si's latest white blood cell value" into the language model, and the language model can be used to extract the white blood cell value from Li Si's physical examination report photo (refer to Figure 5B In addition, the electronic device 100 also inputs the memo information recording the physical examination result of Li Si and the query sentence "Li Si's latest white blood cell value" into the language model, and the white blood cell value can be extracted from the memo information through the language model (refer to Figure 5B In this way, the electronic device 100 can provide multiple search results based on the query statement.

[0281] For another example, the electronic device 100 may obtain the aforementioned Figure 3BThe query statement shown is "AA bank card number". The file content information input by the language model according to prompt1 in the above step S1012 may include: AA bank card number. The file attribute information input by the language model according to prompt2 in the above step S1012 may be empty. The electronic device 100 may input the above file content information into the semantic vector extraction model to determine the semantic vector of the query statement. For example, the semantic vector of the query statement "AA bank card number" can be used to indicate that the semantics of the query statement is: AA bank card number. The electronic device 100 may search the semantic vector that is most similar to the semantic vector of the query statement from the semantic vector database. For example, the semantic vector that the electronic device 100 finds to be most similar to the query statement may be the semantic vector representing AA bank card information. The electronic device 100 may determine the data associated with the most similar semantic vector, namely, the photo of the AA bank card. The electronic device 100 inputs the photo of the AA bank card and the query statement "AA bank card number" into the language model, and the bank card number can be extracted from the photo of the AA bank card through the language model (refer to Figure 3B The bank card number shown is 322A).

[0282] For another example, the electronic device 100 may obtain the aforementioned Fig. 6A For the query statement shown as “Annual Performance Attachment”, the file content information input by the language model according to prompt1 in the above step S1012 may include: annual performance attachment. The file attribute information input by the language model according to prompt2 in the above step S1012 may be empty. The electronic device 100 may input the above file content information into the semantic vector extraction model to determine the semantic vector of the query statement. For example, the semantic vector of the query statement “Annual Performance Attachment” can be used to indicate that the semantics of the query statement is: a file that records annual performance. The electronic device 100 may search the semantic vector database for the most similar semantic vector to the semantic vector of the query statement. For example, the semantic vector that the electronic device 100 finds to be most similar to the query statement may be a semantic vector representing annual performance information. The electronic device 100 may determine the data associated with the most similar semantic vector, namely, a file named “Annualperformance” and a file named “2019Annualperformance”. The electronic device 100 may provide the above searched files to the user as options (refer to Fig. 6A Search results 616 and 617 are shown).

[0283] The information search process of other query statements mentioned in the aforementioned information search scenario of this application can refer to the above exemplary description, which will not be described one by one here.

[0284] By the above Fig.10As can be seen from the method shown, the user can enter a query statement in the electronic device 100 to quickly query and obtain the information they want to query. The electronic device 100 can extract the information that the user wants to search from the files locally on the electronic device 100 and / or in the cloud for the user to use according to the semantics of the query statement. In this way, the user can obtain the information he wants to search through a single search operation, without having to open the corresponding file after the search and then manually extract the information he needs from the file. The above method simplifies the operation of the user searching for information and improves the efficiency of the user in obtaining information.

[0285] Fig.11 The schematic diagram of the architecture of a communication system 1100 provided in an embodiment of the present application is exemplified.

[0286] like Fig.11 As shown, the communication system 1100 may include an electronic device 100 , a server 200 , and a server 300 .

[0287] The electronic device 100 may include a semantic vector extraction model 1111, a semantic vector database 1112, and a language model 1113. Among them, the semantic vector extraction model 1111 can be used to extract the semantic vector of a given content from the given content. For example, the electronic device 100 can extract one or more semantic vectors associated with a file through the semantic vector extraction model 1111. For another example, the electronic device 100 can extract the semantic vector of a query statement through the semantic vector extraction model 1111. The semantic vector database 1112 may store semantic vectors associated with files stored locally on the electronic device 100 and / or in the cloud. The language model 1113 can be used to generate text that meets the requirements according to the prompt. The above-mentioned semantic vector extraction model 1111 and language model 1113 can refer to the introduction of the aforementioned embodiments.

[0288] The server 300 may include a cloud storage space 1131. The cloud storage space 1131 may be a cloud storage space associated with the electronic device 100. For example, a device account is logged into the electronic device 100. The cloud storage space 1131 may be a cloud storage space of a device account logged into the electronic device 100. For another example, a cloud disk application account is logged into the cloud disk application of the electronic device 100. The cloud storage space 1131 may be a cloud storage space of the cloud disk application account.

[0289] The electronic device 100 can communicate with the server 300 to obtain the storage content in the cloud storage space 1131 so as to search the cloud storage space 1131 for the information to be searched by the query statement.

[0290] The server 200 may include a language model 1121. The language model 1121 may refer to the introduction of the above-mentioned embodiment.

[0291] In some embodiments, the electronic device 100 may not include the language model 1113. After obtaining the query statement, the electronic device 100 may send the query statement to the server 200. The server 200 may determine the file content information and the file attribute information from the query statement through the language model. Fig.10 Step S1012 shown in the figure may be executed by the server 200. The server 200 may send the file content information and the file attribute information to the electronic device 100. The electronic device 100 may execute the aforementioned Fig.10 Steps S1013 and S1014 shown in the figure determine the semantic vector 2. Then, the electronic device 100 can determine the data 1 associated with the semantic vector 2, and send the data 1 to the server 200. The server 200 can use the data 1 and the query statement as inputs of the language model, and extract the information to be queried by the query statement from the data 1 through the language model. The server 200 can send the information to be queried by the query statement to the electronic device 100.

[0292] In the case where the electronic device 100 includes the language model 1113, the electronic device 100 may perform Fig.10 In step S1012 and step S1015 shown, information to be queried by the query statement is extracted.

[0293] It is understandable that the various user interfaces described in the embodiments of the present application are only example interfaces and do not limit the present application scheme. In other embodiments, the user interface may adopt a different interface layout, may include more or fewer controls, and may increase or decrease other functional options, as long as they are based on the same inventive concept provided by the present application, they are all within the scope of protection of the present application.

[0294] It should be noted that, without causing any contradiction or conflict, any feature in any embodiment of the present application, or any part of any feature, can be combined, and the combined technical solution is also within the scope of the embodiments of the present application.

[0295] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An information search method, characterized in that: The method comprises: The electronic device receives a first operation, where the first operation is used to search for first content; In response to the first operation, the electronic device displays a first search result on a first page, where the first search result is found based on the first content and includes first information extracted from a first file; The electronic device displays one or more first function controls for using the first information on the first page, and the one or more first function controls are related to the type of the first information.

2. The method according to claim 1, characterized in that: The first operation includes calling out a first search box in the electronic device and inputting the first content in the first search box; or, The first operation includes an operation of selecting and searching the first content; or, The first operation includes an operation of inputting a first symbol at a first position associated with the first content; or, The first operation includes an operation on a query control associated with the first content.

3. The method according to claim 1 or 2, characterized in that: The first search result further includes one or more of the following: the name of the first file, the application to which the first file belongs, and the content of the first file containing the first information.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: In response to the first operation, the electronic device further displays a second search result on the first page, where the second search result is searched based on the first content, and the second search result includes second information extracted from a second file; The electronic device displays one or more second function controls for using the second information on the first page, and the one or more second function controls are related to the type of the second information.

5. The method according to any one of claims 1 to 4, characterized in that The one or more first functional controls include a first copy control, and the first copy control is used to copy the first information.

6. The method according to any one of claims 1 to 5, characterized in that The type of the first information is a telephone number, and the one or more first function controls include a dial control, and the dial control is used to dial the telephone number corresponding to the first information; or, The type of the first information is an address, and the one or more first function controls include a navigation control, and the navigation control is used to navigate to the address corresponding to the first information; or The type of the first information is a bank card number, and the one or more first function controls include a transfer control, and the transfer control is used to transfer money using the bank card number corresponding to the first information.

7. The method according to any one of claims 1 to 6, characterized in that The first content is located on the first page, the one or more first functional controls include a first insertion control, and the method further includes: The electronic device receives the operation on the first insertion control and inserts the first information into the first page.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: The electronic device receives a second operation, where the second operation is used to search for second content, and the second content is located on a second page; In response to the second operation, the electronic device displays a third search result on the second page, where the third search result is searched based on the second content, and the third search result includes a first option corresponding to a third file; In response to an operation on the first option, the electronic device inserts the third file into the second page.

9. The method according to claim 7, characterized in that: The method further comprises: The electronic device receives an operation on the first information inserted on the first page, and displays a source of the first information, wherein the source of the first information includes one or more of the following: the name of the first file, the application to which the first file belongs, and the content of the first file containing the first information.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: The electronic device receives a first instruction from a user, wherein the first instruction is used to instruct to extract information from a fourth file and fill in a third page, wherein the third page includes a first input box; According to the first instruction, the electronic device fills in third information in the first input box, where the third information is information extracted from the fourth file and matches the first input box.

11. The method according to any one of claims 1 to 10, characterized in that Before the electronic device displays the first search result, the method further includes: The electronic device determines file content information and file attribute information according to the first content, wherein the file content information indicates semantic limitation of information to be searched for the first content in the first content, and the file attribute information indicates attribute limitation of information to be searched for the first content in the first content; The electronic device determines a first semantic vector of the first content according to the file content information; The electronic device searches for one or more files according to the file attribute information, and obtains semantic vectors corresponding to the one or more files, where the one or more files include the first file; The electronic device calculates similarity between the semantic vectors corresponding to the one or more files and the first semantic vector, and selects a second semantic vector corresponding to the first file according to the similarity, wherein the second semantic vector is a semantic vector with the highest similarity among the semantic vectors whose similarity to the first semantic vector is higher than a first threshold; The electronic device extracts the first information from the first file according to the first content.

12. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to call the computer program so that the electronic device executes the method according to any one of claims 1 to 11.

13. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 11.

14. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are run on an electronic device, the electronic device executes the method according to any one of claims 1 to 11.

Images