Information searching method and device and electronic equipment

Abstract

The invention discloses an information search method and device and electronic equipment, and the method comprises the steps: responding to a first operation, displaying a search box, and controlling an input cursor to be located in the search box; in response to the first operation, a first search engine responds to each input character located in the search box in real time, first target objects matched with first target characters located in the search box are searched, and the first target characters are all characters in the search box when the input characters are responded; updating the displayed first target object in real time; in response to the second operation, searching a second target object matched with a second target character in the search box by using a second search engine, the second target character being all characters in the search box; a second target object is displayed, the second search engine comprises a first target model, the first target model is at least used for understanding the semantics of the second target character, and the second target object is not the character type.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an information search method, device and electronic device. Background Art

[0002] Users often need to use electronic devices to search for objects such as documents, applications, or pictures.

[0003] In order to ensure the accuracy of information search, currently, after detecting the search command input by the user, the electronic device will use the characters entered in the search box as search keywords to search for objects. However, it takes a certain amount of time for the user to complete the input of the search keyword and for the electronic device to search for objects based on the search keyword, resulting in the user needing a long time to see the search results. Therefore, how to reduce the time spent by the user waiting for the object search results while taking into account the search accuracy, so that the user can view the searched objects in time is a technical problem that needs to be solved by those skilled in the art. Summary of the invention

[0004] In one aspect, the present application provides an information search method, comprising:

[0005] In response to a first operation, a search box is displayed and an input cursor is controlled to be located in the search box;

[0006] In response to the first operation, responding in real time to each input character in the search box with a first search engine, searching for a first target object that matches a first target character in the search box, the first target character being all characters in the search box in response to the input character;

[0007] Update the first target object displayed in real time;

[0008] In response to a second operation, searching with a second search engine for a second target object that matches a second target character in the search box, where the second target character is all the characters in the search box;

[0009] The second target object is displayed, wherein the second search engine includes a first target model, the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type.

[0010] In a possible implementation, the information search method further includes:

[0011] In response to the second operation, if there is at least one terminal device in a valid state, the second target character and a call request for activating the second target model on the terminal device are sent to the at least one terminal device through a communication channel between the at least one terminal device, so that each of the terminal devices can process the second target character based on the second target model.

[0012] In yet another possible implementation, the information search method further includes:

[0013] An index object is obtained through a communication channel with at least one terminal device in a valid state, wherein the index object is used to obtain a third target object, where the third target object is a target object determined by a second target model on the terminal device and matches the second target character.

[0014] In yet another possible implementation, in response to the second operation, searching with a second search engine for a second target object matching a second target character in the search box includes:

[0015] The second target character and the first target object are processed based on the first target model, and a first target object that meets the semantics of the second target character is determined from the first target objects as the second target object.

[0016] In another possible implementation, the searching for the first target object matching the first target character in the search box includes: searching for the first target object whose corresponding character matches the first target character;

[0017] The step of searching for a second target object matching a second target character in the search box with a second search engine includes:

[0018] The second search engine is used to search for a second target object whose corresponding vector feature matches the vector feature corresponding to the second target character located in the search box.

[0019] In yet another possible implementation, the first target model includes a first generative model, and the second target model includes a second generative model;

[0020] The third target object is an object generated by the terminal device based on the second generative model.

[0021] In yet another possible implementation, the information search method further includes:

[0022] If the second search engine does not search for a second target object that matches the second target character in the search box, using the first generative model to generate a second target object that matches the second target character;

[0023] The third target object is an object generated based on the second generative model after the terminal device fails to search for an object matching the second target character.

[0024] In yet another possible implementation, the sending the second target character and the calling request for invoking the second target model on the terminal device to the at least one terminal device through the communication channel between the at least one terminal device includes:

[0025] Based on the intelligent model capability of the at least one terminal device, the second target character and a calling request for invoking the second target model on the terminal device are sent to the at least one terminal device.

[0026] In another aspect, the present application further provides an information search device, comprising:

[0027] A search box display unit, configured to display a search box and control an input cursor to be located within the search box in response to a first operation;

[0028] A first search unit is used to respond to the first operation, using a first search engine to respond in real time to each input character in the search box, and search for a first target object that matches a first target character in the search box, wherein the first target character is all characters in the search box when responding to the input character;

[0029] A first display unit, used for updating the displayed first target object in real time;

[0030] A second search unit, configured to search for a second target object matching a second target character in the search box using a second search engine in response to a second operation, wherein the second target character is all characters in the search box;

[0031] The second display unit is used to display the second target object, wherein the second search engine includes a first target model, the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type.

[0032] In another aspect, the present application also provides an electronic device, comprising:

[0033] Input devices, display screens, and processors;

[0034] Among them, the processor is used to obtain a first operation through the input device; in response to the first operation, a search box is displayed through the display screen and the input cursor is controlled to be located in the search box; in response to the first operation, a first search engine is used to respond to each input character located in the search box in real time, and a first target object matching the first target character located in the search box is searched, and the first target character is all the characters in the search box when responding to the input character; the first target object displayed is updated in real time through the display screen; in response to a second operation obtained through the device, a second search engine is used to search for a second target object matching the second target character located in the search box, and the second target character is all the characters in the search box; and the second target object is displayed through the display screen, wherein the second search engine includes a first target model, and the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0036] Figure 1 A schematic diagram of a flow chart of the information search method provided in this application;

[0037] Figure 2 A schematic diagram of another flow chart of the information search method provided by the present application;

[0038] Figure 3 A schematic diagram of another flow chart of the information search method provided by the present application;

[0039] Figure 4 This is an example diagram of an application of the solution of this application;

[0040] Figure 5 A schematic diagram of the structure of the information search device provided by this application;

[0041] Figure 6 A schematic diagram of another structure of the information search device provided by the present application;

[0042] Figure 7 A schematic diagram of the composition architecture of an electronic device provided in this application. DETAILED DESCRIPTION

[0043] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation mode of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. It is known to those skilled in the art that with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0044] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0045] like Figure 1 , showing a flow chart of the information search method provided in an embodiment of the present application. The method of this embodiment can be applied to electronic devices, which can be user devices such as mobile phones, laptops or tablet computers, or devices such as servers, without limitation.

[0046] The method of this embodiment may include:

[0047] S101, in response to a first operation, displaying a search box and controlling an input cursor to be located in the search box.

[0048] The first operation is an operation for inputting characters to be searched. Since the premise of inputting characters to be searched is that there is a search box and the input cursor is located in the search box, the present application needs to control the input cursor to be located in the displayed search box in response to the first operation so that the user can input the characters to be searched into the search box.

[0049] It is understandable that if the search box is not displayed before the first operation is detected, the search box needs to be displayed and the input cursor needs to be controlled to be located in the search box. For example, the first operation includes: a click operation of clicking an icon for triggering entry into the search mode, and in response to the click operation, the search box is displayed and the input cursor needs to be controlled to be located in the search box.

[0050] If a search box is already displayed before the first operation is detected, the display of the search box can be maintained without repeatedly displaying the search box, and the input cursor needs to be controlled to be located in the search box. For example, if the first operation includes an operation for moving the input cursor to the search box and positioning it, the input cursor can be controlled to be located in the search box.

[0051] S102, in response to a first operation, responding in real time to each input character in a search box with a first search engine, searching for a first target object matching a first target character in the search box.

[0052] It is understandable that inputting characters to be searched involves positioning the input cursor in the search box and inputting characters in the search box once or multiple times, so the first operation may include a continuous input operation lasting a certain length of time, or multiple continuous input actions. Based on this, when the input cursor is located in the search box, the present application will also respond to the first operation, and respond to each input character input into the search box in real time through the first search engine to perform a search operation.

[0053] The first target characters are all the characters in the search box in response to the input characters.

[0054] Based on this, each time the first search engine performs a search operation, all characters currently entered in the search box are used as first target characters, and matching objects are searched based on the first target characters. That is, each time the user performs character input in the search box through the first operation (including inputting new characters or modifying characters, etc.), the first search engine will respond to the currently entered input characters and search for objects matching all the input characters currently contained in the search box.

[0055] In this application, for the sake of distinction, the object searched by the first search engine is referred to as the first target object.

[0056] In the present application, the first target object is not a character, but an entity object other than a character type object, such as a document, a picture, a webpage, or an application. Based on this, the process of the first search engine searching for the first target object matching the first target character is different from searching for a character string that the user may input based on the first target character.

[0057] S103, updating the displayed first target object in real time.

[0058] In the present application, the first search engine can respond to each character entered in the search box in real time. Whenever there is a character input in the search box, the first target object of the first search engine will be triggered, and the first target object searched each time may be different. Therefore, in order to enable the user to intuitively see the objects that currently match all the characters entered in the search box, each time the first search engine responds to the input characters to search for the first target object, it is necessary to display the currently searched first target object to achieve real-time updating of the displayed first target object.

[0059] For example, if a user wants to search for an object that matches "a white cat", then after the user enters "white" in the search box, the first search engine will search for and display the first target object that matches "white". If the user continues to enter "color" in the search box, and "white" is already entered in the search box, the first search engine will search for and display the first target object that matches "white". Similarly, if the user continues to enter "of", the first search engine will search for and display the first target object that matches "white". Finally, when "a white cat" is entered in the search box, the first search engine will search for and display the first target object that matches "a white cat".

[0060] It is understandable that the first search engine may search for one or more first target objects each time. After searching for the first target object each time, if the first search engine searches for multiple first target objects, at least one first target object with the highest matching degree may be displayed in descending order of the matching degree between the first target object and the first target character. For example, a set number (e.g., 10 or 20, etc., which may be set as needed) of the first target objects with the highest matching degree may be displayed each time.

[0061] It is understandable that, in the process of a user inputting characters into the search box, the first target object matching all the characters input into the search box is searched in real time and updated continuously, so that the user can see the search results matching the currently input characters in a timely manner. On this basis, in the process of a user inputting characters into the search box, if the user sees that the object to be searched exists in the displayed first target object, the user can directly click on the corresponding object and view it without continuing to input characters, which improves the efficiency of the user's search for objects.

[0062] S104: In response to the second operation, searching with a second search engine for a second target object that matches a second target character in the search box.

[0063] The second operation is different from the first operation.

[0064] For example, the second operation is an operation for indicating the end of inputting the search string, that is, an operation for indicating the end of the first operation. For example, the second operation may be an operation of inputting Enter, or an operation of clicking a search icon associated with the search box.

[0065] The second target characters are all the characters in the search box, that is, all the characters in the search box when responding to the second operation.

[0066] The second search engine is different from the first search engine. In the present application, the second search engine includes a first target model, and the first target model is at least used to understand the semantics of the second target character. For example, the first target model can be any artificial intelligence model with semantic understanding ability. For example, the first target model can be a neural network model or a large language model, etc., without limitation.

[0067] Accordingly, the second search engine may search for objects matching the semantics of the second target characters based at least on the semantics of the second target characters.

[0068] For the sake of distinction, the object searched by the second search engine is referred to as a second target object.

[0069] In the present application, the second target object is not of character type, that is, the second target object may be an entity object other than a character type object, such as a document, file, picture, web page or application.

[0070] S105, displaying the second target object.

[0071] It is understandable that the second target object searched by the second search engine may be one or more. In the case of searching for multiple second target objects, all of the second target objects may be displayed; if the object display area is relatively limited, the first set number of second target objects with the highest matching degree may also be displayed according to the matching degree with the second target character.

[0072] From the above content, it can be seen that in response to the first operation, the present application can respond to each input character in the search box in real time with the first search engine, search for the first target object that matches all the characters currently in the search box, and update the displayed first target object in real time, so that in the process of the user inputting characters into the search box, as the input characters in the search box change, the target object that matches the characters input by the user can be displayed in real time, so that the user can view the target object that matches the currently input characters in time. Moreover, in response to the second operation, the present application will also search for the second target object that matches all the characters in the search box with the second search engine. Since the second search engine includes a first target model for understanding the semantics of characters, the second search engine can more accurately search for objects that match all the characters in the search box, thereby making up for the situation that the first search engine cannot accurately search for the objects required by the user in real time, thereby achieving the purpose of taking into account both search timeliness and search accuracy, and naturally improving the user's search experience.

[0073] It is understandable that in the present application, after the second target object is searched, only the second target object may be displayed. In order to improve the comprehensiveness of the search results, the present application may also display the first target object that was searched the most recently while displaying the second target object.

[0074] Furthermore, in order to enable users to intuitively understand the search sources of different target objects, when displaying the second target object and the first target object most recently searched, the present application can also respectively indicate the first source information corresponding to the first target object and the second source information corresponding to the second target object. The first source information is used to characterize that the first target object is obtained by searching using the first search engine, and the second source information is used to characterize that the second target object is obtained by searching using the second search engine.

[0075] The first source information may be an icon or character representing the first search engine, and the second source information may be an icon or character representing the second search engine, and there is no limitation on this.

[0076] It is understandable that, when displaying the first target object and the second target object at the same time, the first target object can also be displayed in the first display area of ​​the search result display area, and the second target object can be displayed in the second display area of ​​the search result display interface. On this basis, the first source information can be marked in the first display area, and the second source information can be marked in the second display area.

[0077] If the electronic device is a user device such as a mobile phone, the search result display area may belong to at least part of the display unit of the electronic device. If the electronic device is a server, the search result display area may belong to at least part of the display unit of the client corresponding to the server.

[0078] In the present application, there are many possible ways to implement the second search engine searching for the second target object.

[0079] In a possible implementation, a second search engine is used to search the electronic device for a second target object that matches the second target character. In this case, since the first search engine and the second search engine use different search methods, the second target object searched by the second search engine is different from the first target object, that is, the second target object searched by the second search engine may be partially or completely different from the first target object searched by the first search engine. For example, the second target object searched by the second search engine may include an object that does not belong to the first target object.

[0080] In another possible implementation, in order to improve search efficiency, searching for the second target object with the second search engine can be as follows: processing the second target character and the first target object based on the first target model, and determining a first target object from the first target object that meets the semantics of the second target character as the second target object.

[0081] The first target model processes the second target character and the second target object by determining the semantics of the second target character and matching the semantics of the second target object with the semantics of the second target character. The semantics of the second target object can be predetermined or recognized in real time by the first target model, and there is no limitation on this.

[0082] Among them, the second search engine determines the second target object from the first target object to reduce the object search amount, and can also determine the second target object that better matches the characters entered in the search box from the searched first target object, thereby improving the accuracy of the object search.

[0083] In the present application, there may be many possibilities for the first search engine and the second search engine.

[0084] In a possible implementation, the first search engine can search for the first target object by matching the first target character with the name corresponding to the object, that is, searching for the first target object whose corresponding character matches the first target character. The character corresponding to the object can be the name or identification character of the object. For example, the first search engine can match the first target character with the names of various objects in the electronic device to search for the first target object whose name matches the first target character.

[0085] The second search engine can search for a second target object whose corresponding vector feature matches the vector feature corresponding to the second target character by matching the vector feature of the second target character with the vector feature corresponding to the object.

[0086] For example, based on the first target model in the second search engine, the vector feature corresponding to the second target character can be determined, and the second target object whose vector feature matches the vector feature of the second target character can be determined. The vector feature of the second target character can also be called a feature vector, which can represent the semantics of the second target character.

[0087] Among them, the vector features of an object can represent the object's properties such as the object's content, function, and source. For example, if the object is an application, the vector features of the object can be determined based on the object's application type, name, developer and other attribute information; if the object is a picture, the vector features reflecting the picture content can be obtained by encoding the picture. If the object is a document, the vector features of the document can be determined based on the document content and name, and the semantic information of the document can be reflected through the vector features.

[0088] The vector features of the objects in the electronic device may also be determined in real time by the first target model. In order to improve the search efficiency, the vector features of the objects in the electronic device may be predetermined. For example, an object vector library may be maintained in the electronic device, and the object vector library may include the vector features of each object in the electronic device. Moreover, whenever an object is added to the electronic device, the vector features of the object are determined and added to the object vector library.

[0089] Among them, the second target object matched by the vector feature and the vector feature corresponding to the second target character can be the first set number of objects with the highest matching degree between the vector feature and the vector feature corresponding to the second target character or the object whose matching degree exceeds a set threshold. Of course, there may be other possibilities, which are not limited to this.

[0090] It is understandable that the local objects of the electronic device are limited, so it is likely that the second search engine cannot search for the second target object. Based on this, in the present application, in addition to being able to search for objects based on the second target model, the second search engine can also support object generation. On this basis, the first target model can include a first generative model.

[0091] Accordingly, in response to the second operation, the electronic device may also first use the second search engine to search for a second target object that matches the second target character. If the second search engine does not find the second target object, the first generative model in the second search engine may be used to generate a second target object that matches the second target character.

[0092] For example, the first target model includes a first intelligent model and a first generative model. On this basis, in response to the second operation, the electronic device will first search for a second target object that matches the second target character based on the first intelligent model in the second search engine. For example, the vector features of the second target character are determined based on the first intelligent model in the second search engine, and the second target object is determined based on the vector features of the second target character and the vector features of the object in the electronic device. If the second target object is not found based on the first intelligent model, a second target object that matches the second target character is generated based on the first generative model. For example, an image or text that matches the second target character is generated.

[0093] Among them, in order to use the first intelligent model of the first target model to search for the second target object that matches the second target character, the electronic device can generate a first prompt statement in response to the second operation, and the first prompt statement can include the second target character, and the first prompt statement is used to prompt the first target model to search for an object based on the second target character. Correspondingly, based on the search prompt statement, the first intelligent model in the first target model is used to search for the second target object that matches the second target character. For example, when the first target model is called, the search prompt statement is input so that the first target model searches for the second target object through the first intelligent model.

[0094] Similarly, if the second target object is not searched based on the first target model, the electronic device may generate a second prompt sentence, the second prompt sentence may include the second target character, and the second prompt sentence is used to prompt the generation of an object based on the second target character.

[0095] It should be noted that the first intelligent model and the first generative model can be two independent models. In actual applications, the first intelligent model and the first generative model can also be the same model. In this case, the first intelligent model and the first generative model can both be the first target model, and the first target model not only has semantic recognition capabilities, but also has object generation capabilities.

[0096] In the above embodiments of the present application, the target objects searched by the first search engine and the second search engine may be objects stored or installed locally on the electronic device, such as applications installed on the electronic device, documents, web pages, or pictures stored on the electronic device or in a database maintained by the electronic device.

[0097] In practical applications, considering that the range of objects that can be searched by the electronic device is relatively limited, or the user wants to view objects on other devices, there is also a need to use other terminal devices to synchronously search for objects that match the second target character. Based on this, in the present application, in response to the second operation, if there is at least one terminal device in an effective state, the second target character and a call request for activating the second target model on the terminal device are sent to the at least one terminal device through the communication channel between the at least one terminal device, so that each terminal device can process the second target character based on the second target model.

[0098] Among them, the terminal device in a valid state is a terminal device that has established a communication channel with the electronic device, and the communication channel is in an available state, so that data can be transmitted between the electronic device and the terminal device.

[0099] For example, an electronic device may maintain terminal devices that establish communication channels with the electronic device and the current connection status of the communication channels between each terminal device and the electronic device, and determine at least one terminal device in which the communication channel is in a connected state from the electronic devices that establish communication channels with the electronic device.

[0100] Among them, the second target model on the terminal device in a valid state can be any artificial intelligence model. The second target model can be a model of the same type as the first target model, or a model of a different type, and there is no restriction on this.

[0101] The process of the second target model processing the second target character is similar to the process of the first target model processing the first target character, which will not be described in detail here.

[0102] Furthermore, the electronic device may also obtain the processing result of the second target character returned by the at least one intelligent terminal through the communication channel between the at least one intelligent terminal in the valid state. For ease of understanding, a possible implementation is described below. Figure 2 , shows another implementation flow diagram of the information search method provided in an embodiment of the present application. The method of this embodiment is applied to an electronic device. This embodiment may include:

[0103] S201, in response to a first operation, displaying a search box and controlling an input cursor to be located within the search box.

[0104] S202, in response to the first operation, responding in real time to each input character in the search box with a first search engine, searching for a first target object matching the first target character in the search box.

[0105] The first target characters are all characters in the search box in response to the input character.

[0106] S203, updating the displayed first target object in real time.

[0107] For the above steps S201 to S203, reference may be made to the relevant introduction of the previous embodiment, which will not be repeated here.

[0108] S204: In response to the second operation, searching with a second search engine for a second target object that matches the second target character in the search box.

[0109] The second target characters are all the characters in the search box.

[0110] The second search engine includes a first target model, and the first target model is used at least to understand the semantics of the second target character, and the second target object is not a character type.

[0111] In one possible implementation, the first target model includes a first intelligent model and a first generative model, and the first intelligent model is used in a second search engine to search for a second target object that matches the second target character, such as determining a second target object that semantically matches the second target character from the first target object based on the first intelligent model, or matching a vector feature in an electronic device based on the first intelligent model to match the second target object that matches the vector feature of the second target character.

[0112] Further, if the second target object is not searched based on the first intelligent model, the second target object matching the second target character is generated based on the first generative model, and step S205 is executed.

[0113] For the specific implementation of step S204, please refer to the related introduction of the previous embodiment, which will not be repeated here.

[0114] S205, displaying the second target object.

[0115] S206, in response to the second operation, if there is at least one terminal device in a valid state, the second target character and a call request for activating the second target model on the terminal device are sent to the at least one terminal device through the communication channel between the at least one terminal device, so that each terminal device can process the second target character based on the second target model.

[0116] The terminal device may be a device of the same type as the electronic device, or may be a device of a different type from the electronic device, and there is no limitation on this.

[0117] Among them, the terminal device in the valid state establishes a communication channel with the electronic device, and the communication channel is in an available state capable of transmitting data.

[0118] In a possible implementation, the electronic device may also be a user terminal such as a mobile phone or a laptop computer, and the terminal device in an effective state may be a terminal device that has established an interconnection channel with the electronic device.

[0119] Among them, the interconnection channel is a communication channel established based on the pairing information between the electronic device and the terminal device. The interconnection channel can also be called a device interconnection channel or a device direct connection channel. On the premise that an interconnection channel is established between the electronic device and the terminal device, data can be directly transmitted between the electronic device and the terminal device without the help of a third-party device for data forwarding. Through the interactive channel between the electronic device and the terminal device, file transfer, screen projection, and mutual control can be achieved.

[0120] For example, the interconnection channel can be a direct connection channel established between the electronic device and the terminal device based on Wi-Fi (Wireless Fidelity) direct connection; or, a P2P direct connection channel established based on P2P (peer-to-peer) technology; or, a direct connection channel established with the help of a wireless network or the same local area network, etc. It can also be a direct connection established based on a USB connection between the electronic device and the terminal device using pairing information between the electronic device and the terminal device, without specific restrictions.

[0121] In the case that an interconnection channel is established between the electronic device and at least one terminal device, in response to the second operation, the electronic device sends the second target character and the calling request to each terminal device through the interconnection channel established with each terminal device.

[0122] It should be noted that, in actual applications, step S205 may be executed synchronously with step S204; step S204 may be executed first, and then step S205; or step S205 may be executed first, and then step S204.

[0123] S207: Obtain an index object through a communication channel with at least one terminal device in a valid state.

[0124] The index object is used to obtain a third target object, which is a target object matched with the second target character determined by the second target model on the terminal device.

[0125] For example, the index object may be an object address or link for locating the third target object, or may be an identifier such as the name or thumbnail of the third target object, and there is no limitation on this.

[0126] It can be understood that the process of processing the second target character on the terminal device to determine the third target object may be similar to the process of processing the second target character on the electronic device to determine the second target object.

[0127] For example, the terminal device may search for a third target object that matches the second target character based on the second target model. For example, the terminal device searches for a third target object that matches the semantics of the second target character. In one possible scenario, the second target model includes a second intelligent model, and the terminal device may search for a third target object that matches the second target character based on the second intelligent model.

[0128] For another example, the second target model in the terminal device includes a second generative model. In this case, the third target object may be an object generated by the terminal device based on the second generative model.

[0129] In particular, the terminal device can generate a third target object matching the second target character based on the second generative model when the third target object is not found based on the second intelligent model.

[0130] It is understandable that the model type of the second target model on different terminal devices may be different. For example, the second target model on some terminal devices is a generative model, the second target model on some terminal devices is an intelligent model that only understands character semantics, and the second target model on some intelligent terminals may include a generative model and an intelligent model for understanding character semantics.

[0131] Based on this, in one possible implementation, in order to enable the terminal device in a valid state to reasonably process the second target character and reduce the risk of the terminal device being unable to process the second target character, the electronic device can also send the second target character and a call request for activating the second target model on the terminal device to the at least one terminal device based on the intelligent model capability of the at least one terminal device.

[0132] Among them, the intelligent model capability of the terminal device is used to characterize the model type of the second target model in the terminal device, that is, to characterize the character processing mode that the second target model in the terminal device can support. The character processing mode may include: at least one of the ability to understand character semantics and the ability to generate objects.

[0133] For example, if the second target model in the terminal device includes a second intelligent model, and the intelligent model capabilities of the terminal device include the ability to understand the semantics of characters, in this case, the electronic device can send the second target character to the terminal device and send a call request to the terminal device for invoking the second target model to recognize the semantics of the second target character, so that the terminal device matches the third target object based on the semantics of the second target character.

[0134] If the second target model in the terminal device includes a second generative model, and the intelligent model capability of the terminal device includes the capability to generate objects, the electronic device can send the second target character and a call request for invoking the second target model to generate an object matching the second target character to the terminal device.

[0135] The intelligent model capability of the terminal device may be notified to the electronic device by the terminal device after the terminal device establishes a communication channel with the electronic device. For example, the terminal device sends a capability notification to the electronic device, and the capability notification is used to indicate the intelligent model capability of the terminal device.

[0136] Of course, if the second target model in the terminal device includes a second intelligent model and a second generative model, the electronic device can send the second target character and a call request to activate the second target model to the terminal device, and the call request is used to instruct the terminal device to search for a third target object matching the second target character based on the second intelligent model, and if the third target object cannot be matched based on the second intelligent model, generate a third target object matching the second target character based on the second generative model.

[0137] S208, display the index object.

[0138] The step S208 is an optional step, and its purpose is to enable the user to understand the third target object matching the second target character on the terminal device based on the displayed index object.

[0139] It is understandable that, since the terminal device is triggered to process the second target character while the electronic device matches the second target object, the electronic device can not only match the second target object, but also obtain the index object corresponding to the third target object. Based on this, the electronic device can display the second target object while displaying the index object.

[0140] Furthermore, in order to enable the user to intuitively distinguish the sources of the index object and the second target object, the electronic device may also indicate the second source information of the second target object and the third source information of the index object. The second source information may refer to the above introduction. The third source information is used to indicate that the third target object corresponding to the index object is an object obtained by the terminal device in a valid state based on the second target model.

[0141] In actual application, while displaying the second target object and the index object, the first target object obtained by the most recent search can also be displayed synchronously. Of course, the source information corresponding to each object can also be marked separately.

[0142] In order to facilitate understanding of the solution of the present application and its benefits, an application scenario is introduced below.

[0143] When users use electronic devices, they often need to search for objects such as documents, pictures or applications in the electronic devices. However, the current search method is to match the search keywords input by the user with the names of the objects on the electronic devices, so the timeliness and accuracy of object search are not high. Moreover, if the user has multiple electronic devices, if the user needs to check whether certain objects are in each electronic device separately, the user needs to search for objects on multiple electronic devices separately, which inevitably leads to a high complexity of the search object.

[0144] Based on this, the present application can realize a more comprehensive, efficient and accurate search for objects on multiple electronic devices by taking advantage of the premise that electronic devices can realize direct communication based on device interconnection. Figure 3 Provide detailed explanation.

[0145] like Figure 3 , which shows a flow chart of the information search method of the present application in an application scenario. The method of this embodiment can be applied to electronic devices, which may be terminals such as mobile phones and laptop computers.

[0146] The method of this embodiment may include:

[0147] S301, in response to a first operation, displaying a search box and controlling an input cursor to be located in the search box.

[0148] S302, in response to the first operation, responding in real time to each input character in the search box with a first search engine, searching the electronic device for a first target object whose object name matches the first target character in the search box.

[0149] The first target characters are all the characters in the search box in response to the input characters.

[0150] For example, a device interconnection application for establishing device interconnection may be deployed in the electronic device. Taking the implementation of this embodiment based on the device interconnection application as an example:

[0151] The first operation may be a series of operations in which the user moves the cursor to the search box of the device interconnection application and performs character input, or a series of operations in which the user clicks the search icon and enters the characters to be searched. On this basis, in response to the cursor moving to the search box or clicking the search icon, the device interconnection application may display the search box (or maintain the search box display) and control the input cursor to be located in the search box. On this basis, each time the user performs a character input operation, the first operation is confirmed, and in response to the user's character input, the first search engine is called to search for each first target object in the electronic device whose object name matches the characters entered in the search box.

[0152] The first search engine does not utilize an artificial intelligence model and does not involve a semantic search for the first target characters. Instead, it merely matches the first target characters with object names of various objects present in the electronic device (eg, installed or stored) to determine at least one first target object.

[0153] From the above, it can be seen that the first target object is not a character generated or predicted by the first search engine, but an object that the electronic device actually has.

[0154] S303: Update the displayed first target object in real time.

[0155] For example, at least one first target object currently searched is displayed in real time in the application interface of the device interconnection application of the electronic device, so that the first target object presented in the application interface of the device interconnection application can be continuously updated while the user inputs characters into the search box.

[0156] Combination Figure 4 Description, such as Figure 4 In the example shown, when the user enters "white cat" in the search box, each time the user enters a word, the first search engine will be called to perform keyword matching, match the object name in the electronic device with the characters in the current search box, and display the target object. Based on this, when the user enters "white cat", each time the user enters a word, such as Figure 4 In the application interface of the device interconnection application, the objects in the object display area corresponding to the local keyword search will change once to display the objects matching the search term currently entered by the user in real time.

[0157] S304, in response to the second operation, determining a vector feature of a second target character in the search box using the first target model in the second search engine, and determining a second target object in the electronic device whose vector feature matches the vector feature of the second target character.

[0158] The second target characters are all the characters in the search box in response to the second operation. The vector features of the second target characters can represent the semantics of the second target characters.

[0159] In one possible implementation, the electronic device may pre-construct the vector features of each object in the electronic device. For example, taking a device interconnection application deployed on an electronic device as an example, when the device interconnection application detects the presence of a newly added object (the latest installed or stored object) in the electronic device, the device interconnection application may call the first target model to generate the vector features of the newly added object and store it in the object vector library. On this basis, in response to the second operation, after the device interconnection application calls the first target model to determine the vector features of the second target character, it may determine the second target object whose vector features match the vector features of the second target character based on the vector features of each object in the object vector library.

[0160] The second target object is an object installed or stored in the electronic device, rather than a character-type object.

[0161] S305, displaying the second target object.

[0162] S306, in response to the second operation, if there is currently at least one terminal device that has established a device interconnection channel with the electronic device, the second target character is sent to the at least one terminal device and a call request for invoking the second target model on the terminal device, so that the terminal device searches for a third target object that semantically matches the second target character from the terminal device based on the second target model.

[0163] S307: Based on the device interconnection channel between at least one terminal device, obtain and display the index object corresponding to the third target object returned by the at least one terminal device.

[0164] The index object is used to obtain the third target object. For example, the index object is at least one of a storage address, an installation location, and an object name of the third target object.

[0165] Combination Figure 4 The second operation can be to click on the search icon associated with the search box, and take the electronic device completing the local and interconnected device object search through the device interconnection application as an example. After the user has entered "white cat" into the search box, the user has completed the input of the full search keyword. On this basis, the user can click on the search icon associated with the search box, and the device interconnection application detects that the user clicks on the search icon, and then the first target model can be called to identify the vector features of "white cat", and the vector features of each object in the object vector library can be matched, and the second target object that matches the semantics of "white cat" in the local electronic device is determined, and displayed in the local intelligent search display area in the application interface of the device interconnection application.

[0166] At the same time, in response to the user clicking the search icon, the electronic device will also send the character "white cat" and a call request for calling the intelligent model on the terminal device to the terminal device that has established a device interconnection with the electronic device through the interconnected device application. In response to the call request, the terminal device will call the intelligent model to identify the third target object that matches the semantics of "white cat" and return the index object corresponding to the third target object to the electronic device. The electronic device will display the interconnected device intelligent search in the application interface of its device interconnection application.

[0167] Based on this, after the user completes "white cat" and clicks the search icon, the electronic device will eventually display the objects searched locally based on the keywords, the objects searched locally based on the local intelligent model, and the index objects of the objects searched through the intelligent model through the terminal device that has established device interconnection with the electronic device.

[0168] Corresponding to an information search method of the present application, the present application also provides an information search device.

[0169] like Figure 5 , shows a schematic diagram of a composition structure of an information search device provided by the present application. The device of this embodiment may include:

[0170] A search box display unit 501, configured to display a search box and control an input cursor to be located in the search box in response to a first operation;

[0171] A first search unit 502 is used for responding to the first operation by using a first search engine to respond to each input character in the search box in real time, searching for a first target object that matches a first target character in the search box, where the first target character is all characters in the search box when responding to the input character;

[0172] The first display unit 503 is used to update the displayed first target object in real time;

[0173] A second search unit 504 is configured to search for a second target object matching a second target character in the search box using a second search engine in response to a second operation, wherein the second target character is all characters in the search box;

[0174] The second display unit 505 is used to display the second target object, wherein the second search engine includes a first target model, the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type.

[0175] In a possible implementation, the second search unit is specifically configured to process the second target character and the first target object based on the first target model, and determine a first target object that meets the semantics of the second target character from among the first target objects as the second target object.

[0176] In another possible implementation, the first search unit is specifically configured to search for the first target object whose corresponding character matches the first target character when searching for the first target object matching the first target character in the search box;

[0177] When searching for a second target object matching a second target character in the search box using a second search engine, the second search unit is specifically used to search for a second target object whose corresponding vector feature matches a vector feature corresponding to the second target character in the search box using the second search engine.

[0178] In a possible implementation, the information search device of the present application can be as follows: Figure 6 As shown, Figure 6 Another structural diagram of an information search device is shown.

[0179] exist Figure 6 In addition to the search box display unit 501, the first search unit 502, the first display unit 503, the second search unit 504 and the second display unit 505, the embodiment also includes:

[0180] The calling and sending unit 506 is used to respond to the second operation and, if there is at least one terminal device in a valid state, send the second target character and a calling request for activating the second target model on the terminal device to the at least one terminal device through the communication channel between the at least one terminal device, so that each of the terminal devices can process the second target character based on the second target model.

[0181] Furthermore, the information search device also includes:

[0182] The object obtaining unit 507 is used to obtain an index object through a communication channel between at least one terminal device in a valid state, and the index object is used to obtain a third target object, which is a target object determined by a second target model on the terminal device and matches the second target character.

[0183] In a possible implementation, the first target model includes a first generative model, and the second target model includes a second generative model;

[0184] The third target object corresponding to the index object returned by the object obtaining unit is an object generated by the terminal device based on the second generative model.

[0185] In yet another possible implementation, the information search device further includes:

[0186] An object generation unit, configured to generate a second target object matching the second target character by using the first generative model if the second search engine fails to find a second target object matching the second target character in the search box;

[0187] Correspondingly, the third target object is an object generated based on the second generative model after the terminal device fails to search for an object matching the second target character.

[0188] In another possible implementation, the call sending unit is specifically used to send the second target character and a call request for activating the second target model on the terminal device to the at least one terminal device based on the intelligent model capability of the at least one terminal device.

[0189] The present application also provides an electronic device. Figure 7, which shows a schematic diagram of a composition structure of the electronic device, the electronic device at least includes a processor 701, an input device 702 and a display screen 703;

[0190] Among them, the processor 701 is used to obtain a first operation through the input device; in response to the first operation, a search box is displayed through the display screen and the input cursor is controlled to be located in the search box; in response to the first operation, a first search engine is used to respond in real time to each input character located in the search box, and a first target object matching the first target character located in the search box is searched, and the first target character is all the characters in the search box when responding to the input character; the first target object displayed is updated in real time through the display screen; in response to a second operation obtained through the device, a second search engine is used to search for a second target object matching the second target character located in the search box, and the second target character is all the characters in the search box; and the second target object is displayed through the display screen, wherein the second search engine includes a first target model, and the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type.

[0191] The electronic device may also include a memory 704 for storing programs required for the processor to perform operations.

[0192] Of course, the electronic device may also have Figure 7 There may be more or fewer components, without limitation.

[0193] In some embodiments of the present application, the first search engine is a local search engine of the electronic device, the second search engine is also a local search engine of the electronic device, and the second search engine includes a first target model, which is a large language model, can understand the semantics of the second target character, and can be converted into a target vector feature based on the semantics. The second target object matching the second target character is determined by comparing the target vector feature with the vector feature library.

[0194] Among them, in some implementation examples, the first search engine is a local search engine of the electronic device, and the second search engine is a search engine capability provided by at least one terminal device connected to the electronic device. The electronic device can call the search engine capability provided by at least one terminal device and provide a second target character through the second search engine and the connection channel between the at least one terminal device, so that the second search engine provided by at least one terminal device processes the second target character based on each including the first target model and feeds back the second target object to the electronic device. The target model is a large language model that can understand the semantics of the second target character and can be converted into a target vector feature based on the semantics. The second target object matching the second target character is determined by comparing the target vector feature with the vector feature library.

[0195] A computer program product is also provided in an embodiment of the present application, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the information search methods provided in the embodiments of the present application.

[0196] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any information search method provided in the embodiment of the present application.

[0197] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0198] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0199] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0200] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. An information search method, comprising: In response to a first operation, a search box is displayed and an input cursor is controlled to be located in the search box; In response to the first operation, responding in real time to each input character in the search box with a first search engine to search for a first target object that matches a first target character in the search box, the first target character being all characters in the search box in response to the input character; Update the first target object displayed in real time; In response to a second operation, searching with a second search engine for a second target object that matches a second target character in the search box, where the second target character is all the characters in the search box; The second target object is displayed, wherein the second search engine includes a first target model, the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type.

2. The information search method according to claim 1, further comprising: In response to the second operation, if there is at least one terminal device in a valid state, the second target character and a call request for activating the second target model on the terminal device are sent to the at least one terminal device through a communication channel between the at least one terminal device, so that each of the terminal devices can process the second target character based on the second target model.

3. The information search method according to claim 2, further comprising: An index object is obtained through a communication channel with at least one terminal device in a valid state, wherein the index object is used to obtain a third target object, where the third target object is a target object determined by a second target model on the terminal device and matches the second target character.

4. The information search method according to claim 1, wherein in response to the second operation, searching with a second search engine for a second target object matching a second target character in the search box comprises: The second target character and the first target object are processed based on the first target model, and a first target object that meets the semantics of the second target character is determined from the first target objects as the second target object.

5. The information search method according to claim 1, wherein searching for a first target object matching a first target character in the search box comprises: Searching for a first target object whose corresponding character matches the first target character; The step of searching for a second target object matching a second target character in the search box with a second search engine includes: The second search engine is used to search for a second target object whose corresponding vector feature matches the vector feature corresponding to the second target character located in the search box.

6. The information search method according to claim 3, wherein the first target model comprises a first generative model, and the second target model comprises a second generative model; The third target object is an object generated by the terminal device based on the second generative model.

7. The information search method according to claim 6, further comprising: If the second search engine does not search for a second target object that matches the second target character in the search box, using the first generative model to generate a second target object that matches the second target character; The third target object is an object generated based on the second generative model after the terminal device fails to search for an object matching the second target character.

8. The information search method according to claim 2, wherein the sending the second target character and the calling request for invoking the second target model on the terminal device to the at least one terminal device through the communication channel between the at least one terminal device comprises: Based on the intelligent model capability of the at least one terminal device, the second target character and a calling request for invoking the second target model on the terminal device are sent to the at least one terminal device.

9. An information search device, comprising: A search box display unit, configured to display a search box and control an input cursor to be located within the search box in response to a first operation; A first search unit is used to respond to the first operation, using a first search engine to respond in real time to each input character in the search box, and search for a first target object that matches a first target character in the search box, wherein the first target character is all characters in the search box when responding to the input character; A first display unit, used for updating the displayed first target object in real time; A second search unit, configured to search for a second target object matching a second target character in the search box using a second search engine in response to a second operation, wherein the second target character is all characters in the search box; The second display unit is used to display the second target object, wherein the second search engine includes a first target model, the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type.

10. An electronic device comprising: Input devices, display screens, and processors; Among them, the processor is used to obtain a first operation through the input device; in response to the first operation, a search box is displayed through the display screen and the input cursor is controlled to be located in the search box; in response to the first operation, a first search engine is used to respond to each input character located in the search box in real time, and a first target object matching the first target character located in the search box is searched, and the first target character is all the characters in the search box when responding to the input character; the first target object displayed is updated in real time through the display screen; in response to a second operation obtained through the device, a second search engine is used to search for a second target object matching the second target character located in the search box, and the second target character is all the characters in the search box; and the second target object is displayed through the display screen, wherein the second search engine includes a first target model, and the first target model is at least used to understand the semantics of the second target character, and the second target object is not a character type.

Images