Information retrieval method and apparatus, device, and storage medium

Abstract

The present application relates to the field of terminals, and relates to an information retrieval method and apparatus, a device, and a storage medium, which solve the problem of low information acquisition efficiency during user retrieval. A specific solution comprises: a terminal receives information to be retrieved that is inputted by a user, and displays a first abstract corresponding to the information to be retrieved. When historical retrieval information matching the information to be retrieved was retrieved by the user in the past, the first abstract is used for indicating the difference between a retrieval result corresponding to the information to be retrieved and a retrieval result corresponding to the similar historical retrieval information. When historical retrieval information similar to the information to be retrieved was not retrieved by the user in the past, the first abstract is used for indicating the difference between retrieval results corresponding to the information to be retrieved in two different time periods. The first abstract indicates the difference between two retrieval results, and when the user performs multiple retrievals, the difference between multiple retrieval results can be displayed by means of an abstract, thereby improving the efficiency of acquiring new information by the user.

Description

Information retrieval method, device, equipment and storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on December 8, 2023, with application number 202311691066.5 and application name “An information retrieval method, device, equipment and storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of terminals, and in particular to an information retrieval method, apparatus, device, and storage medium. Background Art

[0003] In the prior art, when a user searches using a search engine, the search engine returns corresponding search results based on the user's query. However, search results often suffer from a header effect, where the first few pages of content are mostly hot topics or newly released content. These hot topics or newly released content may have already been seen by some users, resulting in low search engine efficiency.

[0004] Furthermore, in existing technologies, when users search for the same or similar information multiple times using search engines, the search results returned by the search engines often contain a large amount of identical or similar content. Even if the search results returned by the search engine multiple times contain newly published content, the newly published content may simply be a copy or summary of existing content. This makes it difficult for users to obtain new information when searching for the same or similar information multiple times.

[0005] It can be seen that when users have retrieval needs, the existing technology lacks a method that can enable users to obtain new information with high efficiency.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide an information retrieval method, apparatus, device, and storage medium, which solve the problem of low efficiency in obtaining information when users search.

[0008] According to the first aspect of the embodiment of the present application, an information retrieval method is provided, in which a terminal receives information to be retrieved input by a user and displays a first summary corresponding to the information to be retrieved. Wherein, in the case where the user has retrieved historical retrieval information that matches the information to be retrieved in the past, the first summary is used to indicate the difference between the retrieval result corresponding to the information to be retrieved and the retrieval result corresponding to similar historical retrieval information. In the case where the user has not retrieved historical retrieval information similar to the information to be retrieved in the past, the first summary is used to indicate the difference between the retrieval results corresponding to the information to be retrieved in two different time periods. In the present application, by generating a summary of the information to be retrieved, the user does not need to read a large amount of repeated content, thereby improving the efficiency of the user in obtaining information. And the first summary is used to indicate the difference between the two retrieval results. In the case where the user searches for similar questions multiple times, the difference between the multiple retrieval results can be shown to the user through the summary, so that the user can obtain new information faster, thereby improving the efficiency of the user in obtaining new information.

[0009] In some embodiments, the process of displaying a first summary includes: displaying a second summary and a first control, wherein the second summary is a summary of the first search result; if the second search information exists, the first control is used to prompt the user to obtain a summary of the search result of the updated first search information, and the first summary is displayed after receiving the operation; or, if the second search information does not exist, the first control is used to prompt the user to subscribe to the search results of the first search information, and the first summary is displayed after a preset time after receiving the operation. The user's operation on the first control is received, and in response to the operation, the first summary is displayed. Through the above method, the user can obtain the first summary through operation, giving the user more optional options and improving the user experience.

[0010] In some embodiments, the process of displaying the second summary and the first control includes: sending first search information to a server; receiving the second summary and first indication information from the server, the first indication information being used to indicate whether the second search information exists; displaying the second summary, and displaying the first control based on the first indication information. The first indication information enables the terminal to determine the content that the first control should display, thereby providing a better user experience using the first control.

[0011] In some embodiments, the process of displaying the first summary includes: sending a second indication message to the server in response to an operation; receiving the first summary from the server; wherein, if the second search information exists, the second indication message indicates an update of the summary of the search results of the first search information; or, if the second search information does not exist, the second indication message indicates a subscription to the search results of the first search information. The second indication message enables the server to generate the corresponding first summary, so that the terminal can obtain the corresponding first summary.

[0012] In some embodiments, the second summary can also be generated by the terminal. Specifically, the second summary is generated based on the first search information; the second summary is a summary of the first search result; based on the first search information, a point of interest matching result is obtained. The point of interest matching result indicates whether there is a second search information that contains the same point of interest as the first search information. The first control is displayed based on the point of interest matching result. This allows for local point of interest matching and protects user privacy.

[0013] In some embodiments, the first summary can also be generated by the terminal. Specifically, the terminal obtains a first search result corresponding to the first search information; receives a user operation on the first control; when the first control is used to prompt an update of the summary of the search result of the first search information, obtains a second search result corresponding to the second search information, and generates a first summary based on the first search result and the second search result; or, when the first control is used to prompt a subscription to the search result of the first search information, obtains the second search result corresponding to the first search information after a preset time, and generates a first summary based on the first search result and the second search result. In this way, the terminal can meet the needs of different scenarios and improve the user experience.

[0014] In some embodiments, the process of generating the first summary by the terminal may specifically include: using the first search result, the second search result, and the first data as input, and generating the first summary through an artificial intelligence model; wherein the first data includes at least one of the following: the first search information, user feedback information, and points of interest; if the second search information is present, the feedback information is used to indicate the user's interaction information with the page corresponding to the second search result; or, if the second search information is not present, the feedback information is the user's interaction information on the page corresponding to the first search result. Generating the first summary by using multiple information in this way can make the generated first summary more accurate and improve the user experience.

[0015] According to a second aspect of an embodiment of the present application, an information retrieval method is provided, which is applied to a server, and the method includes: receiving first retrieval information from a terminal; sending a first summary corresponding to the first retrieval information to the terminal; wherein the first summary is used to indicate the difference between the first retrieval result and the second retrieval result, and the first retrieval result is the retrieval result of the first retrieval information retrieved at the first time; wherein, in the case where the second retrieval information exists, the second retrieval result is the retrieval result of the second retrieval information; or, in the case where the second retrieval information does not exist, the second retrieval result is the retrieval result of the first retrieval information retrieved at the second time, the second time is later than the first time, and the second retrieval information is retrieval information that has the same point of interest as the first retrieval information retrieved by the user before receiving the first retrieval information.

[0016] In some embodiments, before sending the first summary corresponding to the first retrieval information to the terminal, the method also includes: generating a second summary based on the first retrieval information; the second summary is a summary of the first retrieval result; obtaining a point of interest matching result based on the first retrieval information, and the point of interest matching result is used to indicate whether there is second retrieval information with the same point of interest as the first retrieval information; sending the second summary to the terminal, and sending first indication information to the terminal based on the point of interest matching result, and the first indication information is used to indicate whether there is second retrieval information.

[0017] In some embodiments, before sending the first summary corresponding to the first retrieval information to the terminal, the method also includes: obtaining the first retrieval result corresponding to the first retrieval information; receiving second indication information from the terminal; when the second indication information is used to indicate updating the summary of the retrieval result of the first retrieval information, obtaining the second retrieval result corresponding to the second retrieval information, and generating a first summary based on the first retrieval result and the second retrieval result; or, when the second indication information is used to indicate subscribing to the retrieval result of the first retrieval information, obtaining the second retrieval result corresponding to the first retrieval information after a preset time, and generating a first summary based on the first retrieval result and the second retrieval result.

[0018] In some embodiments, generating a first summary based on the first search result and the second search result includes: taking the first search result, the second search result and the first data as input, and generating the first summary through an artificial intelligence model; wherein the first data includes at least one of the following: first search information, user feedback information and points of interest, and in the case where the second search information exists, the feedback information is used to indicate the user's interaction information with the page corresponding to the second search result; or, in the case where the second search information does not exist, the feedback information is the user's interaction information on the page corresponding to the first search result.

[0019] According to a third aspect of an embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the information retrieval method of the first aspect or the second aspect mentioned above.

[0020] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. The computer program is used to implement the information retrieval method of the first or second aspect above.

[0021] According to the fifth aspect of the embodiment of the present application, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in an electronic device, the processor in the electronic device executes the above-mentioned information retrieval method.

[0022] According to a sixth aspect of the embodiments of the present application, an information retrieval device is provided, which has the function of implementing the terminal or server behavior described in the method of the first or second aspect. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions, such as a receiving module, a processing module, a sending module, and a display module.

[0023] It should be understood that the technical solutions provided in the above-mentioned second aspect, third aspect, fourth aspect, fifth aspect, and sixth aspect, and their technical features can all correspond to the methods provided in the first aspect and its optional implementation methods, so the beneficial effects that can be achieved are similar and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] FIG1 is a flow chart of an information retrieval method provided by the related art;

[0025] FIG2 is a flowchart of a summary generation method provided by the related art;

[0026] FIG3A is a simplified schematic diagram of a system architecture provided in an embodiment of the present application;

[0027] FIG3B is a structural diagram of a terminal provided in an embodiment of the present application;

[0028] FIG3C is a structural diagram of a server provided in an embodiment of the present application;

[0029] FIG4 is a simplified schematic diagram of another system architecture provided in an embodiment of the present application;

[0030] FIG5 is a flow chart of an information retrieval method provided in an embodiment of the present application;

[0031] FIG6 is a schematic diagram of a search interface provided in an embodiment of the present application;

[0032] FIG7 is a flowchart of another information retrieval method provided in an embodiment of the present application;

[0033] FIG8 is a schematic diagram of another information retrieval interface provided in an embodiment of the present application;

[0034] FIG9 is a schematic diagram of another information retrieval interface provided in an embodiment of the present application;

[0035] FIG10 is a schematic diagram of an information retrieval method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In the related art, users can often use search engines to retrieve the information they want to know. The process of user retrieval in the related art is: the terminal receives the search information entered by the user in the search engine's web page or the input box of the client, and receives the user's search operation, such as a click or touch operation on the search button. In response to the above search operation, the terminal sends a search request to the server, and the search request carries the search information entered by the user. After receiving the user's search information, the server searches the search information through the search engine to obtain the search results. The search results generally include multiple links. The server sends the search results to the terminal, and the terminal displays the search results after receiving the search results.

[0037] Because search results include multiple links, users often need to view the content within the links to obtain the information they want, and there may be a large amount of duplicate content within the multiple links, making it less efficient for users to obtain the information they want through search results. Furthermore, search engine results often exhibit a header effect, meaning that the content on the first few pages is mostly hot results or the latest published content. However, the latest published content does not necessarily represent an update; it may simply be a copy or summary of existing content. This means that these results may be content that users have already seen or are not interested in, and may not necessarily be what they need or meet their needs. This means that users may need to read a large amount of content to obtain the information they want, making it less efficient for users to obtain information through search.

[0038] Furthermore, when searching, users always expect to obtain new information, rather than repetitive, familiar information. However, in some cases, if users cannot obtain valid information from the current search results, they may use a different expression to search for similar information as the previous search. Furthermore, in some cases, users may search for the same or similar information at different times in order to obtain the latest information. If users frequently search for the same or similar information, the search results from different searches will contain a large amount of duplicate content, which also reduces the efficiency of users in obtaining new information.

[0039] It can be seen that in the information retrieval method of the related technology, the efficiency of users in obtaining information is low, especially in the process of multiple retrievals, users cannot quickly obtain new information.

[0040] To improve search efficiency, enhance user information acquisition efficiency, and enhance user experience, related technologies can use artificial intelligence models to summarize search results for quick browsing and filtering. For example, see Related Technologies 1 and 2 below.

[0041] In related technology 1, as shown in FIG1 , the server obtains and analyzes user search logs, and establishes or updates a user interest model based on a concept clustering method. That is, the server determines the keywords of the content that the user is interested in from the content that the user has searched in the past. The server then analyzes the similarity between the user's interest and the sentences in the search results based on the user interest model and the search results to obtain the current search results. The inverse document frequency (IDF) of the search keyword is calculated. The amount of information in the sentence is calculated. Using the similarity between the user interest model and the sentences in the search results, the search keyword IDF, and the amount of information in the sentence, a personalized sentence scoring processing method is adopted to generate a personalized summary that satisfies the user. This allows the related technology to generate summaries that are more in line with the interests of different users based on their interest models. For example, if a user has read a lot of content related to planting in the past, when the user searches for a certain information, content related to planting will be extracted from the search results, and a summary will be generated based on the content related to planting.

[0042] While the above method can improve the user's information acquisition efficiency by generating summaries based on user interests and the current search results through an artificial intelligence model, it does not address the problem of duplicate search results across multiple searches. Furthermore, in this method, the user interest model is generated based on the user's historical searches, making the generated summary more likely to be related to the user's historical browsing history, which may further exacerbate the problem of duplicate search results across multiple searches. This results in users seeing a lot of duplicate information in the summaries they see when searching for the same or similar information multiple times. This fails to improve the user's efficiency in acquiring new information across multiple searches, impacting the user's search experience.

[0043] In addition to the aforementioned related technology 1, another related technology 2 for generating summaries in news push scenarios will be introduced here. Referring to Figure 2, the server can determine the user's target news category based on the user's historical access data; match the target news category with a preset event graph to obtain multiple news items related to the target news category; extract a news summary from each news item to obtain multiple news summaries; filter out some news summaries from the multiple news summaries, and generate a briefing based on these news summaries.

[0044] Although Related Technology 2 is also a method for generating summaries, this method can only generate briefings for target news categories corresponding to the preset event map, and cannot cover all content that the user is interested in. It lacks flexibility and breadth and cannot be applied to the search engine scenario of this application. In addition, similar to the method of Related Technology 1, this method does not distinguish between duplicate content, resulting in the possibility of duplicate information in briefings generated multiple times for the same user, making it inefficient for users to obtain new information and affecting the user experience.

[0045] It can be seen that the related art lacks a method for improving the efficiency of user retrieval and acquisition of new information.

[0046] The present application proposes an information retrieval method, the main contents of which include: a terminal receives information to be retrieved input by a user and displays a first summary corresponding to the information to be retrieved. Specifically, if the user has previously retrieved historical retrieval information that matches the information to be retrieved, the first summary is used to indicate the differences between the retrieval results corresponding to the information to be retrieved and the retrieval results corresponding to similar historical retrieval information. If the user has not previously retrieved historical retrieval information similar to the information to be retrieved, the first summary is used to indicate the differences between the retrieval results corresponding to the information to be retrieved in two different time periods.

[0047] In this application, by generating a summary of the information to be retrieved, users do not need to read a large amount of repeated content, thereby improving the efficiency of users in obtaining information. The first summary is used to indicate the differences between the two search results. If a user searches for similar questions multiple times, the summary can be used to show the differences between the multiple search results to the user, allowing the user to obtain new information more quickly, thereby improving the efficiency of users in obtaining new information.

[0048] It should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution of this application complies with the provisions of relevant laws and regulations and does not violate public order and good morals. For example, in the technical solution of this application, the processing of user personal information is carried out with the user's authorization, which is explained here and will not be repeated below.

[0049] For the application scenario of this application, the method of this application can be executed by a terminal, or can be implemented by interaction between a terminal and a server. Next, the system architecture of the embodiment of this application will be described in detail by taking the method of this application implemented by interaction between a terminal and a server as an example.

[0050] FIG3A is a simplified schematic diagram of a system architecture to which embodiments of the present application can be applied. As shown in FIG3A , the system architecture may include: at least one terminal 31 and at least one server 32 .

[0051] The structure of the terminal 31 can be seen in FIG3B . As shown in FIG3B , the terminal 31 may include a processor 311, an internal memory 312, a communication module 313, a sensor module 314, and a display screen 315. The communication module may include a first antenna, a second antenna, a radio frequency submodule, a communication submodule, a modem, and a baseband processor, and the sensor module 314 may include at least a touch sensor.

[0052] The structure shown in the embodiment of the present invention does not limit the terminal 31. It may include more or fewer components than shown, or some components may be combined or separated, or arranged differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0053] The processor 311 may include one or more processing units. For example, the processor 311 may include an application processor (AP), a modem processor, a graphics processing unit (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). Different processing units may be independent devices or integrated into the same processor.

[0054] The controller is the decision-maker that directs the various components of terminal 31 to coordinate operations according to instructions. It serves as the nerve center and command center of terminal 31. Based on instruction opcodes and timing signals, the controller generates operational control signals to control instruction fetching and execution.

[0055] Processor 311 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor is a high-speed cache memory. This can store instructions or data that have just been used or are being recycled by the processor. If the processor needs to use the instruction or data again, it can directly call it from the memory. This avoids duplicate accesses, reduces processor latency, and thus improves system efficiency.

[0056] In some embodiments, the processor 311 may include an interface, which may include an inter-integrated circuit (I2C) interface, a mobile industry processor interface (MIPI), and / or a general-purpose input / output (GPIO) interface.

[0057] The I2C interface is a bidirectional synchronous serial bus that includes a serial data line (SDA) and a serial clock line (SCL). In some embodiments, the processor may include multiple I2C busses. For example, the processor may be coupled to a touch sensor via the I2C interface, enabling communication between the processor and the touch sensor via the I2C bus interface to implement touch functionality on terminal 31.

[0058] The MIPI interface can be used to connect the processor to peripheral devices such as the display screen 315 and the camera. The MIPI interface can include a display serial interface (DSI) for the display screen 315. In some embodiments, the processor and the display screen 315 communicate via the DSI interface to implement the display function of the terminal 31.

[0059] The GPIO interface can be configured through software. The GPIO interface can be configured as a control signal or a data signal. In some embodiments, the GPIO interface can be used to connect the processor to the display 315, a communication module, a sensor, etc. The GPIO interface can also be configured as an I2C interface, a MIPI interface, etc.

[0060] The interface connection relationship between the modules shown in the embodiment of the present invention is for illustrative purposes only and does not limit the structure of the terminal 31. The terminal 31 may adopt different interface connection modes or a combination of multiple interface connection modes in the embodiment of the present invention.

[0061] In some embodiments, the processor 311 can be used to execute the information retrieval method of the embodiments of the present application. The processor 311 can also communicate with other sensors or the display screen 315 through various interfaces, such as communicating with a touch sensor through an I2C interface to obtain the information to be retrieved input by the user. For example, the processor 311 can communicate with the display screen 315 through a GPIO interface so that the first summary can be displayed to the user through the display screen 315.

[0062] The internal memory 312 can be used to store computer executable program code, which includes instructions. The processor 311 executes various functional applications and data processing of the terminal 31 by running the instructions stored in the internal memory 312. The memory 312 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system, an application required for at least one function (such as a search engine application), etc. The data storage area can store data created during the use of the terminal 31, etc. In addition, the memory 312 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, other volatile solid-state storage devices, a universal flash storage (UFS), etc.

[0063] The wireless communication function of the terminal 31 can be implemented through the communication module 313, that is, the first antenna, the second antenna, the radio frequency submodule, the communication submodule, the modem and the baseband processor.

[0064] The first antenna and the second antenna are used to transmit and receive electromagnetic wave signals. Each antenna in terminal 31 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, a cellular network antenna can be reused as a wireless local area network diversity antenna. In some embodiments, the antenna can be used in conjunction with a tuning switch.

[0065] The RF submodule can provide a communication processing module for wireless communication solutions including 2G / 3G / 4G / 5G applied on the terminal 31. It can include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The RF module receives electromagnetic waves from the first antenna, filters, amplifies and processes the received electromagnetic waves, and transmits them to the modem for demodulation. The RF module can also amplify the signal modulated by the modem and convert it into electromagnetic waves for radiation through the first antenna. In some embodiments, at least some functional modules of the RF submodule can be set in the processor 311. In some embodiments, at least some functional modules of the RF submodule can be set in the same device as at least some modules of the processor 311.

[0066] A modem may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium- or high-frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to a baseband processor for processing. In some embodiments, the modem may be a standalone device. In some embodiments, the modem may be independent of the processor and housed in the same device as the RF module or other functional modules.

[0067] The communication submodule can provide a communication processing module for wireless communication solutions including wireless local area networks (WLAN), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc. applied on the terminal 31. The communication submodule can be one or more devices integrating at least one communication processing module. The communication module receives electromagnetic waves via the second antenna, frequency modulates and filters the electromagnetic wave signal, and sends the processed signal to the processor. The communication submodule can also receive the signal to be sent from the processor, frequency modulate it, amplify it, and convert it into electromagnetic waves for radiation via the second antenna.

[0068] In some embodiments, the first antenna of the terminal 31 is coupled to the radio frequency module, and the second antenna is coupled to the communication module. This allows the terminal 31 to communicate with the network and other devices via wireless communication technologies. The wireless communication technologies may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, WLAN, and / or IR technology.

[0069] Through the communication module 313, the terminal can communicate with the server. For example, in some embodiments, the terminal can send the information to be retrieved to the server, and the terminal can receive the first summary, the first search result, the second search result, etc. sent by the server.

[0070] A touch sensor, also known as a "touch panel," may be provided on display screen 315 to detect touch operations applied to or near it. The detected touch operations may be communicated to an application processor to determine the type of touch event and provide a corresponding visual output via display screen 315.

[0071] Through the touch sensor, the terminal can obtain the information to be retrieved input by the user.

[0072] Terminal 31 implements its display functionality through a GPU, display screen 315, and an application processor. The GPU is a microprocessor for image processing that connects display screen 315 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 311 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0073] Display screen 315 can be used to display the first summary, first search results, etc. Display screen 315 includes a display panel. The display panel can be an LCD (liquid crystal display), an OLED (organic light-emitting diode), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a MiniLED, a MicroLED, a Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, terminal 31 can include one or N display screens, where N is a positive integer greater than one.

[0074] The terminal may display the first summary to the user via the display screen 315 , thereby enabling the user to obtain new information more efficiently.

[0075] The structure of the server can be seen in FIG3C . As shown in FIG3C , the server 32 may include: a processing module 321 , a storage module 322 and a communication module 323 .

[0076] The processing module 321 is the control center of the server. For example, the processing module 321 can be any one or a combination of CPU, GPU, field-programmable gate array (FPGA) and application-specific integrated circuit (ASIC).

[0077] The storage module 322 is used to store data. For example, the storage module 322 can be used to store user usage data and data corresponding to multimedia content. The storage module 322 can also store computer instructions. The processing module 321 reads and executes the computer instructions stored in the storage module 322 to implement server functions, such as obtaining search results and generating a first summary.

[0078] The communication module 323 is used for the server to communicate with the terminal, or for communicating with other servers. In some embodiments, the system may include a first server and a second server, wherein the first server is deployed with a search engine and is responsible for performing information retrieval, and the second server is responsible for generating a summary based on the retrieval results.

[0079] Figures 3B and 3C divide the device structure of the application system of the present application from a hardware perspective. Next, in conjunction with Figure 4, the server of the application system of the present application will be structurally divided from a functional perspective. And the scheme of the embodiment of the present application will be briefly described. It should be noted that Figure 4 is only an example and does not represent a limitation of the present application. For example, in addition to the scheme shown in Figure 4, it is easy to understand that multiple functions in Figure 4 can also be implemented by multiple servers. For example, the system includes a first server and a second server. The first server is deployed with a search engine module 41 for implementing the function of information retrieval, and the second server is deployed with a summary generation module 42 for implementing the function of generating a summary.

[0080] As shown in FIG4 , server 32 includes a search engine module 41 and a summary generation module 42. Search engine module 41 is configured to receive a request from terminal 31 containing information to be retrieved, retrieve the information to be retrieved, and return the search results to the terminal. Search engine module 41 may also send the search results to summary generation module 42. The information to be retrieved is also referred to as the first search information in this application.

[0081] The summary generation module 42 may include a data submodule 421 and a model submodule 422 .

[0082] The data submodule 421 includes a storage unit 4211 and a processing unit 4212. The storage unit 4211 is used to store the search results and corresponding information to be retrieved sent by the search engine. The processing unit 4212 is used to process the data into a data format that can be processed by the model submodule 422.

[0083] The processing unit 4212 can receive search results from the search engine module 41, and can also receive requests including information to be retrieved from the terminal 31. Based on the requests, the processing unit 4212 processes the information to be retrieved and the search results into a data format that can be processed by the model sub-module 422. The processing unit 4212 can also communicate with the storage unit 4211 and can store processed data in the storage unit 4211. The processing unit 4212 can also retrieve the stored processed data from the storage unit 4211 and forward it to the model sub-module 422.

[0084] The storage unit 4211 can store data so that the model submodule 422 can determine whether the user has searched for historical search information that matches the current search information based on the data stored in the storage unit 4211. In some embodiments, the storage unit 4211 can store historical search information and search results corresponding to each user, so as to generate the first summary in a subsequent process.

[0085] In some embodiments, the processing unit 4212 processes the data, which may be to convert the data into an embedding format, that is, to perform vector processing on data in a text format or the like.

[0086] Model submodule 422 can obtain data from data submodule 421 and determine whether there is any historical search information that matches the information to be retrieved, that is, whether there is any second search information that shares the same interest point as the information to be retrieved. Model submodule 422 can also generate a first summary based on the data sent by data submodule 421, such as the first and second search results sent.

[0087] In some embodiments, the model submodule 422 may include a matching unit 4221 and a summary generation unit 4222 .

[0088] Matching unit 4221 is used to determine whether there is second search information that matches the information to be retrieved. For example, matching unit 4221 can use an artificial intelligence model to determine whether the user has retrieved historical search information that is similar or identical to the subject of the information to be retrieved, based on the information to be retrieved, the search results corresponding to the information to be retrieved, the historical search information, and the search results corresponding to the historical search information, based on the information to be retrieved, sent by processing unit 4212. In other words, determine whether there is historical search information that matches the information to be retrieved. For another example, based on the information to be retrieved and the historical search information sent by processing unit 4212, the information to be retrieved and the historical search information can be compared for similarity to determine whether the user has retrieved similar historical search information. Matching unit 4221 can also be used to obtain points of interest corresponding to the information to be retrieved, or to obtain points of interest common to the information to be retrieved and the historical search information.

[0089] The summary generation unit 4222 is used to generate a first summary. In some embodiments, the summary generation unit 4222 may also generate a second summary. The meanings and generation methods of the first and second summaries will be described in detail below and will not be repeated here.

[0090] The summary generating unit 4222 can generate a first summary based on the first search result and the second search result, wherein the first summary is used to indicate the difference between the first search result and the second search result. The first search result and the second search result are search results corresponding to matching search information retrieved by the user in different time periods.

[0091] After generating the first digest or the second digest, the digest generating unit 4222 may send the generated first digest or the second digest to the processing unit 4212 , and the processing unit 4212 may forward the first digest or the second digest to the terminal 31 .

[0092] In this way, the terminal can display to the user the search results corresponding to the information to be retrieved that matches twice, so that the user can quickly obtain new information, thereby improving the user's usage experience.

[0093] It should be noted that the above briefly describes the system used in this application through an example of interaction between a terminal and a server. This application can also be applied to a terminal, that is, the terminal completes the functions of the above-mentioned search engine module 41 and the summary generation module 42. The above-mentioned embodiment does not represent a limitation of this application.

[0094] Next, the information retrieval method shown in this application will be described through an exemplary embodiment. As shown in Figure 5, Figure 5 is a flowchart of an information retrieval method shown in this application according to an exemplary embodiment, including the following steps:

[0095] Step 501: Receive information to be retrieved input by a user.

[0096] The method shown in Figure 5 is applied to a terminal. The user is the user who uses the terminal, the information to be retrieved is the query, and the information to be retrieved is also referred to as the first search information in this application. The information to be retrieved is the information input by the user and retrieved using the search engine, that is, the information entered in the search box of the page corresponding to the search engine. The page can be the search box of the web page corresponding to the search engine of the terminal, or it can be the search box in the application corresponding to the search engine, or it can be the search box in the negative first screen of the terminal. As for the specific form of the information to be retrieved, the information to be retrieved can be a short sentence or phrase composed of text, and the short sentence or phrase is used to indicate the content that the user wants to retrieve, such as the information to be retrieved can be "Chinese General Large Model", "Chinese General Large Model Benchmark", etc. Taking the search on the negative first screen of the terminal as an example, as shown in Figure 6, the information to be retrieved is the information entered in the search box 61.

[0097] Receiving the information to be retrieved input by the user may be, when receiving the user's search operation, obtaining the information to be retrieved input by the user. Specifically, the search operation may be an operation of the user on the search control, such as a click operation. Obtaining the information to be retrieved input by the user may be, obtaining the information to be retrieved input by the user in the search box. In conjunction with Figure 6, as shown in Figure 6, the user may first enter the information to be retrieved in the search box 61, and then click on the search control 62 in the interface. The user clicking on the search control 62 is also the user's click operation on the search control. After detecting the user's click operation on the search control 62, the terminal may obtain the information to be retrieved input by the user in the search box 61.

[0098] Step 502 : Display a first summary based on the information to be retrieved. The first summary is used to indicate the difference between a first search result and a second search result. The first search result is the search result of the information to be retrieved retrieved at the first time.

[0099] Wherein, if there is historical search information that matches the information to be retrieved, the second search result is the search result of the historical search information that matches the information to be retrieved; or, if there is no historical search information that matches the information to be retrieved, the second search result is the search result of the information to be retrieved retrieved at a second time, the second time being later than the first time. The above-mentioned matching historical search information is the search information that the user retrieved before receiving the first search information and has the same point of interest as the information to be retrieved.

[0100] The historical search information that matches the information to be searched is also referred to as second search information in this application. Historical search information refers to search information that was searched before the user entered the information to be searched. For example, the information to be searched in step 501 may be the information to be searched that was entered by the user at 12:00 on November 1st, and the historical search information may be the information to be searched that was entered by the user before 12:00 on November 1st.

[0101] Points of interest can be used to indicate the subject of the search information. The historical search information that matches the information to be searched is, in other words, the search information that the user has searched for in the past with the same or similar subject as the information to be searched. For example, the information to be searched in step 501 can be the "Chinese General Model" input by the user at 12:00 on November 1st, and the historical search information that matches the information to be searched can be the "Chinese General Model" input by the user at 12:00 on October 29th, or the "Benchmark of the Chinese General Model" input by the user at 12:00 on October 30th, etc. The specific method for determining whether there is historical search information that matches the information to be searched can be found in the following text and will not be described in detail here.

[0102] The first summary in this application can be generated by the terminal or by the server. In the case where the first summary is generated by the server, the terminal can also send the information to be retrieved to the server after step 501, so that the server can search based on the information to be retrieved and generate the first summary based on the search results. After the server generates the first summary, the terminal can receive the first summary from the server. Sending the information to be retrieved to the server can be sending a search request to the server, and the search request carries the information to be retrieved.

[0103] If the first summary is generated by the terminal and the search results are provided by the server, after step 501, the terminal may send the information to be retrieved to the server and receive the search results from the server. The search results received from the server may include a first search result and a second search result. In other words, the server may store the user's past historical search information and corresponding search results, and based on the stored historical search information and corresponding search results, determine whether there is historical search information that matches the information to be retrieved, and send the corresponding first search result and second search result to the terminal. The terminal may then generate a first summary based on the received first search result and second search result.

[0104] If the first summary is generated by the server and the search results are retrieved by the terminal, the user's search history, that is, the user's historical search information and corresponding search results, can be stored in the terminal. After step 501, the terminal can determine whether there is historical search information that matches the information to be retrieved based on the stored data, and send the information to be retrieved, the first search results, the second search results, etc. to the server, so that the server can generate the first summary based on the received information. Storing the search results in the terminal can ensure user privacy.

[0105] In the case where the method is implemented only by a terminal, after step 501 , the terminal may generate a first digest.

[0106] The search results refer to the content corresponding to the multiple links retrieved. For example, if a search for a specific piece of information yields five links, the search results refer to the text within those five links. In some cases, the search results include a large amount of content, and summaries can be generated based on only a portion of the search results to reduce processing pressure. The corresponding first and second search results refer to the search results for the same or similar information that the user has searched for at different time periods.

[0107] Specifically, if the user has previously searched for historical search information with similar or identical topics to the information being searched before entering the information to be searched, that is, if there is historical search information that matches the information being searched, the first search result will be the search result corresponding to the information being searched at the first time, and the second search result will be the search result corresponding to the historical search information that the user has previously searched for that matches the information being searched. If the user has previously searched for historical search information that matches the information being searched multiple times, the second search result may be the search result corresponding to the historical search information that matched the information being searched most recently.

[0108] In this case, the first summary is used to show the user how the first search result has been updated relative to the second search result. Displaying the first summary, when a user searches for information to be retrieved, displays the updates to the current search result compared to previous search results in the results returned to the user. This allows the user to quickly access different information from different searches, improving the user's efficiency in obtaining information, especially new information, and enhancing the user experience.

[0109] If the user has not searched for matching information before entering the information to be searched, the first search result is the search result corresponding to the information to be searched in step 501. The first search result may be the search result for the information to be searched generated immediately after step 501 is executed. The second search result is the search result for the information to be searched generated some time after step 501 is executed, such as a search result obtained for the information to be searched one week or one month later. In other words, the second search result is the search result for the information to be searched obtained at a second time, a period of time after the first time.

[0110] In this case, the first summary is used to show the user an update of the second search result relative to the first search result. Displaying the first summary, i.e., displaying updated search results corresponding to previously searched information to the user via push or other means some time after the user has retrieved the information, allows the user to access new information more quickly. This proactive push also allows users to access new information without searching, improving the user experience.

[0111] In addition, as for the specific method of generating the first summary, it can be generated through an artificial intelligence model, that is, generated through generative artificial intelligence (artificial intelligence generated content, AIGC), for example, it can be generated through a large language model.

[0112] Specifically, the first search result and the second search result can be used as input, and the artificial intelligence model can be used to obtain a first summary indicating the difference between the first search result and the second search result. In addition, the first search result, the second search result and the first data can be used as input, and the artificial intelligence model can be used to generate a first summary. The first data includes at least one of the following: information to be retrieved, user feedback information and points of interest. In the case where there is historical search information that matches the information to be retrieved, the feedback information is used to indicate the user's interaction information with the page corresponding to the second search result; or, in the case where there is no historical search information that matches the information to be retrieved, the feedback information is the user's interaction information with the page corresponding to the first search result. If there is no historical search information that matches the information to be retrieved, the points of interest input to the artificial intelligence model are the points of interest corresponding to the information to be retrieved.

[0113] User feedback information refers to user interaction information on the page corresponding to the search results when the user searches for the information to be searched corresponding to a certain point of interest, such as the user clicking on or adding a link to a favorite, or the user hovering over a certain location. If the user has previously searched for information to be searched that matches the information to be searched, the above-mentioned interaction information refers to the interaction information in the search results of the user's previously searched historical search information that matches the information to be searched. If the user has not previously searched for information to be searched that matches the information to be searched, the above-mentioned interaction information refers to the interaction information on the page corresponding to the first search result output after executing step 501.

[0114] These interactive information can be regarded as content that users are interested in. By inputting user feedback information into the artificial intelligence model, the output summary can be made more targeted, more in line with the user's interests, and the diversity of summaries corresponding to different users can be improved.

[0115] Points of interest are the topics corresponding to the information being retrieved. For example, if the information being retrieved is "Chinese General Model," the corresponding point of interest could be "Chinese Language Model." If the user has previously searched for information that matches the information being retrieved, points of interest are the common topics between the matching information and the information being retrieved. For example, if the user has previously searched for "Benchmark of Chinese General Model," and the information being retrieved is "Chinese General Model," the common point of interest between the two is "Chinese Language Model."

[0116] By inputting at least one of the points of interest and the information to be retrieved into the artificial intelligence model, the model can determine the content of the information to be retrieved, so that the generated summary can be closer to the information to be retrieved, and the first summary can be more in line with the user's needs, thereby improving the user's usage experience.

[0117] When the first data includes information to be retrieved, user feedback information and points of interest, more information can be provided to the artificial intelligence model so that the generated summary is more in line with user needs, thereby bringing a better user experience.

[0118] In addition, if the user has retrieved historical search information that matches the information to be retrieved in the past, and if a summary of the historical search information is stored, the summary of the historical search information can also be input into the artificial intelligence model, so that the generated summary is more in line with user needs, thereby bringing a better user experience.

[0119] The display of the first summary may be to display the entire content of the first summary. For example, if there is historical search information that matches the information to be searched, the first summary may be directly displayed to the user after receiving the information to be searched.

[0120] Displaying the first summary may also be displaying partial content of the first summary, or the title of the first summary. For example, when the full text of the first summary needs to be displayed, and the full text of the first summary cannot be fully displayed on one page, only partial content of the first summary may be displayed. For another example, when the user has not retrieved historical search information that matches the information to be retrieved before step 501, a period of time after step 501 is executed, the first summary may be generated, and the first summary may be used to indicate the difference between the second search result of the information to be retrieved at the current second time and the second search result of the information to be retrieved at the first time. In the above case, the first summary may be displayed by a push method, and then displaying the first summary may be displaying the title of the first summary or partial content of the first summary in the push box, and after the user clicks the push box, the full content of the first summary may be displayed.

[0121] Next, we will take the system shown in Figure 4 as an example and combine it with a specific embodiment to illustrate an information retrieval method shown in an embodiment of the present application. As shown in Figure 7, Figure 7 is a flowchart of an information retrieval method shown in a specific embodiment of the present application, including the following steps:

[0122] Step 701: The terminal receives information to be retrieved input by the user.

[0123] The specific implementation of step 701 can be found in the above description of step 501 and will not be repeated here.

[0124] Step 702: The terminal sends a search request to the server based on the acquired information to be searched.

[0125] The retrieval request is a request including the information to be retrieved. Accordingly, the server needs to receive the information to be retrieved from the terminal, that is, the server can receive the retrieval request including the information to be retrieved from the terminal.

[0126] As shown in Figure 4, the server includes a search engine module 41 and a summary generation module 42. In some embodiments, the retrieval request may include a retrieval request sent to the search engine module 41 and a retrieval request sent to the summary generation module 42. The retrieval request sent to the search engine module 41 is used to trigger the search engine module 41 to search the information to be retrieved and obtain a first retrieval result. The retrieval request sent to the summary generation module 42 is used to trigger the summary generation module 42 to match the information to be retrieved and determine whether there is historical retrieval information that matches the information to be retrieved, that is, to determine whether there is historical retrieval information that has the same interest point as the information to be retrieved. In some other embodiments, the retrieval request may also be a retrieval request sent to the search engine module 41. After the search engine module 41 completes the retrieval, it sends the first retrieval result and the information to be retrieved to the summary generation module 42, so that the summary generation module 42 can determine whether the user has retrieved historical retrieval information that matches the information to be retrieved based on the first retrieval result, the information to be retrieved, the stored historical retrieval information, and the corresponding retrieval result.

[0127] Step 703: The server obtains a first search result corresponding to the information to be retrieved.

[0128] Step 704: The server obtains a point of interest matching result based on the first search information.

[0129] The point of interest matching result is used to indicate whether there is historical search information that has the same point of interest as the information to be searched.

[0130] The first search result is the search result corresponding to the information to be searched, that is, the search result obtained by the search engine module 41 based on the information to be searched. In step 703, the server may obtain the first search result corresponding to the information to be searched.

[0131] The point of interest matching result is used to indicate whether the user has retrieved historical retrieval information that matches the information to be retrieved in the past. In addition, in order to facilitate the processing of subsequent steps, the point of interest matching result may include historical retrieval information that matches the information to be retrieved or the identifier of the historical retrieval information, so as to facilitate the subsequent steps to determine the second retrieval result. In the case where there is a historical retrieval with the same point of interest as the information to be retrieved, the point of interest matching result may also include the common point of interest of the information to be retrieved and the above-mentioned historical retrieval information, and the point of interest is used to facilitate the subsequent generation of the first summary. In addition, in the case where there is no historical retrieval with the same point of interest as the information to be retrieved, the point of interest matching result may also include the point of interest, where the point of interest refers to the point of interest corresponding to the information to be retrieved, that is, the subject of the information to be retrieved, and the point of interest may also facilitate the subsequent generation of the first summary.

[0132] 4 , step 703 may be performed by the search engine module 41 in FIG4 , and step 704 may be performed by the summary generation module 42 in FIG4 . In the above case, after step 703 is performed, the search engine module 41 may also send the first search result to the summary generation module 42 .

[0133] Step 703 is executed in response to the search request. Step 704 can be executed in response to the search request sent by the terminal, or in response to the first search result and the information to be searched sent by the search engine module 41.

[0134] The specific implementation method of step 704 may be to compare the similarity between the information to be retrieved and the historical retrieval information, identify the historical retrieval information whose similarity with the information to be retrieved exceeds a threshold, and determine that the historical retrieval information is the historical retrieval information sharing the same point of interest as the information to be retrieved. Alternatively, a clustering method may be used to determine the cluster to which the information to be retrieved belongs, thereby determining the historical retrieval information that meets the above conditions.

[0135] When the point of interest matching results include points of interest, the points of interest can be obtained through the artificial intelligence model. For example, when it is determined that the user has retrieved historical retrieval information with a similarity greater than a threshold with the information to be retrieved in the past, the historical retrieval information with a similarity greater than a threshold with the information to be retrieved and the information to be retrieved are input into the artificial intelligence model to obtain the above-mentioned points of interest through the artificial intelligence model.

[0136] POI matching results can also be obtained through an artificial intelligence model. For example, the information to be retrieved and the historical search information can be used as input to obtain the POI matching results through the artificial intelligence model. Alternatively, the information to be retrieved, the search results corresponding to the information to be retrieved, the historical search information, and the search results corresponding to the historical search information can be used as input to obtain the POI matching results through the artificial intelligence model. If the POI matching results include POIs, the POI matching results including the POIs can be directly obtained through the artificial intelligence model.

[0137] The artificial intelligence model used to obtain the point of interest matching results can be the same as the artificial intelligence model used to generate the first summary above, for example, it can also be obtained through a large language model.

[0138] Corresponding to FIG4 , the above-mentioned step of obtaining the point of interest matching result may be performed by the matching unit 4221 in FIG4 . Specifically, the processing unit 4212 may receive the first search result and the information to be retrieved from the search engine module 41, or the processing unit 4212 may receive the information to be retrieved from the terminal and process the received data. The processing unit 4212 may also obtain the historical search information stored in the storage unit 4211 and the search results corresponding to the historical search information. The processing unit 4212 may send the processed data and the obtained historical search information and the search results corresponding to the historical search information to the matching unit 4221. The matching unit 4221 may determine the point of interest matching result based on the data sent by the processing unit 4212.

[0139] The above specific implementation process is only an example and does not limit the present application.

[0140] Step 705: The server generates an initial summary based on the information to be retrieved.

[0141] The initial abstract is also the second abstract in this application, that is, the abstract of the first search result, and is used to summarize the first search result. In addition, the initial abstract may also include the basis for generating the initial abstract, so that users can more conveniently obtain information.

[0142] Here we will give a specific example to illustrate the initial summary. In the case where the information to be retrieved is "Chinese General Large Model", the initial summary may include the following:

[0143] The Chinese general large model refers to a large-scale pre-trained language model that can perform well on multiple Chinese natural language processing tasks, such as text classification, reading comprehension, dialogue, generation, etc.

[0144] Currently, numerous research institutions and companies in China have developed various general-purpose large-scale Chinese models and tested and compared them on various benchmarks. SuperCLUB is a comprehensive benchmark specifically for general-purpose large-scale Chinese models. It evaluates models based on basic capabilities, specialized capabilities, and Chinese-specific capabilities, and provides both human-based benchmarks and automated evaluation methods. According to the latest SuperCLUB evaluation results, the following leading general-purpose Chinese large-scale models are currently available: Model 1, Model 2, and Model 3. These models all demonstrate certain capabilities in question-answering, conversational, and generative learning, but they also have limitations and deficiencies that require further improvement.

[0145] Answer source: Web page 1, Web page 2.

[0146] The source of the above answer can be a link that jumps to the corresponding page after clicking. It can be seen that the initial summary can help users understand the information to be retrieved more quickly and improve the user experience.

[0147] Regarding the method for generating the initial summary, the server may use the first search result, the information to be searched, and the points of interest as input and generate the initial summary using an artificial intelligence model. The initial summary may also be generated using methods known in the relevant art, and this application does not limit the method for generating the initial summary.

[0148] With reference to Figure 4 , step 705 described above may be generated by summary generation unit 4222. Specifically, summary generation unit 4222 may obtain the matching results from matching unit 4221, as well as data such as the to-be-retrieved information and the first search results from processing unit 4212, and generate an initial summary based on the artificial intelligence model. Alternatively, matching unit 4221 may send the matching results and input information from matching unit 4221 to summary generation unit 4222, so that summary generation unit 4222 can generate an initial summary based on this information.

[0149] In some embodiments, the summary generating unit 4222 needs to generate the first and second summaries described above, and can determine whether to generate the first or second summary based on the input data to the summary generating unit 4222. For example, if the input data formats in the two scenarios differ, or if a flag is added to the input data to indicate whether the first or second summary is currently being generated, the summary generating unit 4222 can generate corresponding summaries based on the data in different formats.

[0150] Step 706: The server sends the first search result to the terminal.

[0151] Step 707: The server sends an initial summary to the terminal, and sends first indication information to the terminal according to the POI matching result.

[0152] The first indication information is used to indicate whether there is historical search information having the same interest point as the information to be searched.

[0153] Correspondingly, the terminal may receive the first search result, the initial summary and the first indication information. Corresponding to FIG4 , step 706 may be executed by the search engine module 41 , and step 707 may be executed by the summary generation module 42 .

[0154] In some embodiments, step 706 is optional, that is, only the initial summary and the first indication information may be returned to the terminal. In other embodiments, the terminal may also obtain and display the first search result so that the user can obtain more information from the first search result.

[0155] It should be noted that the execution order of the above steps 703-707 does not limit the present application. For example, the server may first generate and send an initial summary to the terminal, and then send the first search result to the terminal. It may first obtain the point of interest matching result and then obtain the first search result, etc.

[0156] Step 708: The terminal displays the initial summary and the first control.

[0157] The initial summary is a summary of the first search result. If there is historical search information matching the information to be searched, the first control is used to prompt the user to obtain an updated summary of the search results of the first search information. The updated summary is displayed after the operation is received. Alternatively, if there is no second search information, the first control is used to prompt the user to subscribe to the search results of the first search information. The updated summary is displayed after a preset time after the operation is received.

[0158] The update summary is also referred to as the first summary in this application. After receiving the user's to-be-retrieved information, the terminal can display the summary corresponding to the to-be-retrieved information, also known as the initial summary, and can prompt the user that the terminal can also display the update summary, allowing the user to quickly obtain new information through the update summary. In addition, displaying the initial summary first can also help users better accept new features and provide a better user experience.

[0159] If the user has previously searched for information with the same interest as the information being searched, the first control can be used to prompt the user to display an update summary. In this case, the first control may display content such as "Detected that related content has been searched before, generating an update summary for me." For example, see Figure 8 , where control 801 in (a) of Figure 8 is the first control.

[0160] If the user has not previously searched for historical information with the same interest as the information being searched, the first control can prompt the user to subscribe to updates on the search results corresponding to the information being searched. In this case, the first control can display content such as "Track changes after one month." For example, see Figure 9 , where control 901 in (a) of Figure 9 is the first control.

[0161] In addition to displaying the initial summary and the first control, the terminal may also display the first search result. For example, the search result may be displayed after the initial summary and the first control so that the user can further view the search result.

[0162] In addition, the first control can be specifically displayed according to the first indication information above. When the first indication information indicates that there is historical retrieval information that matches the information to be retrieved, the first control can be used to prompt an update summary. When the first indication information indicates that there is no historical retrieval information that matches the information to be retrieved, the first control can be used to prompt the user to subscribe to changes in the retrieval results of the first retrieval information.

[0163] Step 709: The terminal receives the user's operation on the first control.

[0164] The above operation may be a trigger operation on the first control, such as a click, a slide, etc. Referring to FIG8 and FIG9 , the above operation may be a click operation on control 801 or control 901 .

[0165] Step 710: In response to the above operation, the terminal sends second indication information to the server.

[0166] In which, when there is historical retrieval information that matches the information to be retrieved, the second indication information is used to indicate updating the summary of the retrieval results of the information to be retrieved; or, when there is no historical retrieval information that matches the information to be retrieved, the second indication information is used to indicate subscribing to the retrieval results of the information to be retrieved.

[0167] Correspondingly, the server needs to receive the second indication information from the terminal. Corresponding to FIG4 , the summary generation module 42 may receive the second indication information.

[0168] Specifically, if the user interacts with the first control, it can be determined that the user wants to obtain an updated summary. In the case where the first control is control 801 in Figure 8, that is, the first control is used to prompt the user to obtain a summary of the retrieval results of the updated first retrieval information, the terminal can, in response to the above operation, send a second indication message to the server indicating the summary of the retrieval results of the updated information to be retrieved. In the case where the first control is control 901 in Figure 9, that is, the first control is used to prompt the user to subscribe to the retrieval results of the first retrieval information, the terminal can, in response to the above operation, send a second indication message to the server indicating the subscription to the retrieval results of the information to be retrieved.

[0169] Step 711: Generate an update summary.

[0170] Specifically, step 711 may be step 7111 or step 7112. That is, either step 7111 or step 7112 may be performed. The updated abstract is also the first abstract in this application.

[0171] Step 7111: When the second indication information is used to indicate updating the summary of the retrieval result of the information to be retrieved, the server obtains the second retrieval result corresponding to the historical retrieval information matching the information to be retrieved, and generates an updated summary based on the first retrieval result and the second retrieval result.

[0172] Step 7112, when the second indication information is used to indicate the subscription to the retrieval result of the information to be retrieved, obtain the second retrieval result corresponding to the information to be retrieved after a preset time, and generate an update summary based on the first retrieval result and the second retrieval result.

[0173] That is, if the user has previously searched for historical search information that matches the information to be searched, the server can immediately generate an update summary based on the second indication information from the terminal. If the user has not previously searched for historical search information that matches the information to be searched, the server can generate an update summary based on the second indication information from the terminal after a preset period of time, so that the user can track the aforementioned changes.

[0174] The specific method for generating the update summary can be found in the description of step 502 above and will not be repeated here. Corresponding to Figure 4, steps 7111 and 7112 may be performed by the summary generation unit 4222 in Figure 4. A specific example will be given here to illustrate the generation process.

[0175] Processing unit 4212 in FIG4 can integrate embedded data into summary generation unit 4222. Specific input data may include: the user's information to be retrieved, such as the "Chinese General Large Model"; search results corresponding to the information to be retrieved; corresponding points of interest, such as the "Chinese Large Language Model"; historical user information obtained based on the points of interest, such as the search results and summaries corresponding to the user's historical search information; and user feedback.

[0176] As for the specific form of the update summary, it may include text that prompts the user to update the content, and may also include the first time and the second time. Here, the update summary will be described through a specific embodiment.

[0177] When the information to be retrieved by the user is "Chinese General Large Model", the update summary may include:

[0178] "Good morning, today is x month x day of xxxx year. The Chinese Universal Large Model has been updated since your last search (yyyy year y month y day):

[0179] First, the Model 4 was released.

[0180] Model 4 is the second-generation version of the open-source Chinese-English bilingual dialogue model released by Company X last month. The new version of Model 4 has significantly improved performance, with inference speed increased by 42%.

[0181] Second, the Model 5 evaluation list is updated.

[0182] In the past month, Model 5 has released its own evaluation scores. Model 5 has significantly surpassed Model 6 and other models on the Chinese evaluation list, and is significantly ahead of Model 7 on the English authoritative evaluation list.

[0183] Step 712: The server sends the update summary to the terminal.

[0184] Correspondingly, the terminal needs to receive the update summary from the server. Specifically, it can be the update summary sent to the terminal by the summary generation module 42 in FIG. 4 .

[0185] Step 713: The terminal displays the update summary.

[0186] After receiving the update summary, the terminal may display the update summary. It should be noted that if the user has previously searched for historical search information that matches the information to be searched, steps 7112, 712, and 713 may be executed immediately. If the user has not previously searched for historical search information that matches the information to be searched, steps 7111, 712, and 713 may be executed some time after step 710 is executed.

[0187] The method for displaying the update summary on the terminal can be found in the above description and will not be repeated here.

[0188] As shown in Figures 8 and 9, in the case where the user has previously retrieved historical retrieval information that matches the information to be retrieved, as shown in Figure 8, an update summary can be generated and displayed based on the user's operation on the first control 801 in (a) of Figure 8. As shown in Figure 8 (b), after the user clicks the first control 801, the content shown in Figure 8 (b) can be displayed, making it easier for the user to obtain new information, thereby providing the user with a better user experience. In the case where the user has not previously retrieved historical retrieval information that matches the information to be retrieved, as shown in Figure 9, an update summary can be generated at a second time after a preset time (i.e., one month) based on the user's operation on the first control 901 in (a) of Figure 9, and displayed to the user through push or other means. After the user clicks on the push, the terminal can expand the push and display the content shown in Figure 9 (b).

[0189] Figure 10 is a summary of the above-mentioned specific embodiments. As shown in Figure 10, in the above-mentioned specific embodiments, the information to be retrieved can be input through the search box in Figure 10. Matching can be performed on the information to be retrieved to obtain a point of interest matching result. For the information to be retrieved, a first search result can also be obtained through a search engine. The point of interest matching result and the information to be retrieved are input into the summary generation model to obtain an initial summary. The terminal can display the initial summary and can display the first control as shown in Figure 10 based on the first indication information for indicating the point of interest matching result. After the terminal receives the user's operation on the first control, it can generate a second indication information, and then generate an updated summary based on the second indication information and the stored data, and the terminal displays the updated summary as shown in Figure 10. The solid-line box in Figure 10 represents data, and the dotted-line box represents the performed action.

[0190] The present application also provides an information retrieval device, which has the function of implementing the terminal or server behavior in the above-mentioned information retrieval method. The function can be implemented by hardware, or it can be implemented by hardware executing the corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions, for example, a receiving module, a processing module, a sending module, a display module, etc. In the case where the device is used to implement the terminal function, the receiving module can execute the above-mentioned steps 501, 701, and 709, the display module can be used to execute the above-mentioned steps 502, 708, and 713, and the sending module can be used to implement steps 702 and 710. In the case where the device is used to implement the server function, the processing module can be used to implement steps 703, 704, 705, and 711, and the sending module can be used to execute steps 706 and 712.

[0191] The present application also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the above-mentioned information retrieval method.

[0192] The present application also provides a computer-readable storage medium, on which a computer program is stored, and the computer program is used to implement the above-mentioned information retrieval method.

[0193] The present application also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in an electronic device, the processor in the electronic device executes the above-mentioned information retrieval method.

[0194] The above is only a specific embodiment of the present application, but the scope of protection of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An information retrieval method, characterized in that: Applied to a terminal, the method comprises: receiving first search information input by a user; Displaying a first summary according to the first search information; the first summary is used to indicate the difference between a first search result and a second search result, the first search result being the search result of the first search information retrieved at the first time; Among them, when there is second retrieval information, the second retrieval result is the retrieval result of the second retrieval information; or, when the second retrieval information does not exist, the second retrieval result is the retrieval result of the first retrieval information retrieved at a second time, the second time is later than the first time, and the second retrieval information is the retrieval information with the same point of interest as the first retrieval information retrieved by the user before receiving the first retrieval information.

2. The method according to claim 1, characterized in that The displaying of the first summary according to the first search information includes: Displaying a second summary and a first control, wherein the second summary is a summary of the first search result; Receiving an operation of the first control by a user; In response to the operation, displaying the first summary; In which, when the second retrieval information exists, the first control is used to prompt the user to obtain a summary of the retrieval results of the updated first retrieval information, and the first summary is displayed after receiving the operation; or, when the second retrieval information does not exist, the first control is used to prompt the user to subscribe to the retrieval results of the first retrieval information, and the first summary is displayed after a preset time of receiving the operation.

3. The method according to claim 2, characterized in that The displaying of the second summary and the first control according to the first search information includes: Sending the first search information to a server; receiving the second summary and first indication information from the server, where the first indication information is used to indicate whether the second search information exists; The second summary is displayed, and the first control is displayed according to the first indication information.

4. The method according to claim 2 or 3, characterized in that: In response to the operation, displaying the first summary includes: In response to the operation, sending second indication information to the server; receiving the first digest from the server; Wherein, when the second search information exists, the second indication information is used to indicate updating the summary of the search results of the first search information; or, when the second search information does not exist, the second indication information is used to indicate subscribing to the search results of the first search information.

5. An information retrieval method, characterized in that: Applied to a server, the method comprises: receiving first search information from a terminal; Sending a first summary corresponding to the first search information to the terminal; The first summary is used to indicate the difference between a first search result and a second search result, the first search result being the search result of the first search information retrieved at a first time; wherein, in the case where the second search information exists, the second search result is the search result of the second search information; or, in the case where the second search information does not exist, the second search result is the search result of the first search information retrieved at a second time, the second time is later than the first time, and the second search information is the search information retrieved by the user before receiving the first search information and having the same point of interest as the first search information.

6. The method according to claim 5, characterized in that Before sending the first summary corresponding to the first search information to the terminal, the method further includes: Generate a second summary according to the first search information; the second summary is a summary of the first search result; Acquire a point of interest matching result according to the first search information, wherein the point of interest matching result is used to indicate whether there is second search information that has the same point of interest as the first search information; The second summary is sent to the terminal, and first indication information is sent to the terminal according to the interest point matching result, where the first indication information is used to indicate whether the second search information exists.

7. The method according to claim 5 or 6, characterized in that: Before sending the first summary corresponding to the first search information to the terminal, the method further includes: Obtaining a first search result corresponding to the first search information; receiving second indication information from the terminal; In a case where the second indication information is used to indicate updating the summary of the retrieval results of the first retrieval information, the second retrieval result corresponding to the second retrieval information is obtained, and a first summary is generated based on the first retrieval result and the second retrieval result; or, in a case where the second indication information is used to indicate subscribing to the retrieval results of the first retrieval information, the second retrieval result corresponding to the first retrieval information is obtained after a preset time, and a first summary is generated based on the first retrieval result and the second retrieval result.

8. The method according to claim 7, characterized in that The generating a first summary according to the first search result and the second search result includes: Using the first search result, the second search result and the first data as input, and generating the first summary through an artificial intelligence model; Among them, the first data includes at least one of the following: the first search information, the user's feedback information and the point of interest. When the second search information exists, the feedback information is used to indicate the interaction information between the user and the page corresponding to the second search result; or, when the second search information does not exist, the feedback information is the interaction information of the user on the page corresponding to the first search result.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the information retrieval method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to implement the information retrieval method according to any one of claims 1 to 8.

Images