Information processing method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to an information processing method and device, equipment and a storage medium. The method comprises the following steps: in response to receiving an input message, determining a group of candidate results matched with the input message; constructing first prompt information based on the input message and the group of candidate results; providing first prompt information to a target model to determine at least one target result from the group of candidate results, the target model being finely tuned based on the group of sample requests and annotation information, the annotation information indicating a sorting result of the group of sample results corresponding to the corresponding sample requests; and generating a response to the input message based on the at least one target result. In this way, the intention of the user can be more accurately understood, the accuracy and efficiency of recommending the interest points are improved, and the search experience of the user is improved.

Description

Information processing method, device, equipment and storage medium Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to information processing methods, apparatuses, devices, and computer-readable storage media. Background Art

[0002] With the development of mobile Internet and location-based service technologies, more and more users use search engines to find nearby places, stores, and other points of interest (POIs). Therefore, how to find POIs based on user intent has become a hot topic.

[0003] Summary of the Invention

[0004] In a first aspect of the present disclosure, a method for information processing is provided. The method includes: in response to receiving an input message, determining a set of candidate results that match the input message; constructing first prompt information based on the input message and the set of candidate results; providing the first prompt information to a target model to determine at least one target result from the set of candidate results, the target model being fine-tuned based on a set of sample requests and annotation information, the annotation information indicating a ranking result of the set of sample results corresponding to the corresponding sample request; and generating a response to the input message based on the at least one target result.

[0005] In a second aspect of the present disclosure, a device for information processing is provided. The device includes: a determination module configured to, in response to receiving an input message, determine a set of candidate results that match the input message; a construction module configured to construct first prompt information based on the input message and the set of candidate results; a processing module configured to provide the first prompt information to a target model to determine at least one target result from the set of candidate results, the target model being fine-tuned based on a set of sample requests and annotation information, the annotation information indicating a ranking result of a set of sample results corresponding to the corresponding sample request; and a generation module configured to generate a response to the input message based on the at least one target result.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of the present disclosure, a computer program product is provided, which includes computer-executable instructions, which, when executed by a processor, implement the method according to the first aspect of the present disclosure.

[0009] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] FIG1 shows a schematic diagram of an example environment in which embodiments according to the present disclosure may be implemented;

[0012] FIG2 shows a flowchart of an example information processing process according to some embodiments of the present disclosure;

[0013] 3A and 3B are schematic diagrams illustrating an example information processing process according to some embodiments of the present disclosure;

[0014] FIG4 shows a schematic structural block diagram of an example information processing device according to some embodiments of the present disclosure; and

[0015] FIG5 shows a block diagram of an electronic device capable of implementing various embodiments of the present disclosure. DETAILED DESCRIPTION

[0016] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0017] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0019] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects shall comply with the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms them. Accordingly, when implementing the various embodiments of the present disclosure, the types, scope of use, and usage scenarios of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method may vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0020] If this specification and the solutions in the examples involve the processing of personal information, such processing will be done only with a legitimate basis (such as with the consent of the subject of personal information or as necessary for the performance of a contract) and only within the prescribed or agreed scope. A user's refusal to process personal information other than that required for basic functions will not affect the user's use of basic functions.

[0021] Traditional POI searches are mostly based on keyword matching, using a post-ranking strategy to recommend shops that best meet the user's needs to the top of the list. However, user requests are often diverse, and traditional solutions fail to truly understand user intent. Consequently, in many scenarios, the recommended shops are not the ones the user desires.

[0022] Embodiments of the present disclosure propose an information processing scheme. According to the scheme, in response to receiving an input message, a set of candidate results matching the input message is determined; first prompt information is constructed based on the input message and the set of candidate results; the first prompt information is provided to a target model to determine at least one target result from the set of candidate results, the target model being fine-tuned based on a set of sample requests and annotation information indicating a ranking result of the set of sample results corresponding to the corresponding sample request; and a response to the input message is generated based on the at least one target result.

[0023] In this way, the embodiments of the present disclosure can more accurately understand the user's intention, improve the accuracy and efficiency of recommending points of interest, and enhance the user's search experience.

[0024] Various example implementations of this solution are described in detail below in conjunction with the accompanying drawings.

[0025] Sample Environment

[0026] FIG1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in FIG1 , the example environment 100 may include an electronic device 110 and a target model 120 .

[0027] In this example environment 100, the electronic device 110 can receive input information. The input information can be information input by a user carrying the user's intention. The input information can be any appropriate type of information, such as voice, text, etc., which will not be described in detail here.

[0028] In some embodiments, the electronic device may determine a set of candidate results that match the input information based on the input information. Furthermore, the electronic device may construct first prompt information input to the model based on the set of candidate results and the input information, thereby determining at least one target result from the set of candidate results to generate a response result to the input message.

[0029] In some embodiments, the electronic device 110 may establish a communication connection with the target model 120. That is, the electronic device 110 may call a local or remote target model 120 to obtain an input message from the electronic device 110 and convert the input message into a corresponding response result.

[0030] In some embodiments, the electronic device 110 can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the electronic device 110 can also support any type of interface for the user (such as "wearable" circuitry, etc.).

[0031] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the present disclosure.

[0032] Example Process

[0033] FIG2 shows a flow chart of an example information processing process 200 according to some embodiments of the present disclosure. Process 200 may be implemented at electronic device 110 or other suitable electronic devices. Process 200 is described below with reference to FIG1 .

[0034] FIG2 shows a flow chart of an information processing process 200 according to some embodiments of the present disclosure. The process 200 may be implemented in the electronic device 110 or other suitable electronic devices. The process 200 is described below with reference to FIG1 .

[0035] As shown in FIG. 2 , at block 210 , the electronic device 110 , in response to receiving an input message, determines a set of candidate results that match the input message.

[0036] In some embodiments, the input information may be any appropriate type of information, such as text information, voice information, etc.

[0037] In some embodiments, the input information may include a corresponding intent, and the electronic device may determine a set of candidate results that meet the intent based on the intent corresponding to the input information.

[0038] In some embodiments, the input message may indicate a request to obtain a point of interest (POI), where the POI may be any appropriate type of POI, such as a store, tourist attraction, hotel, etc. In some embodiments, the set of candidate results may be a set of candidate POIs that match the input message. For example, if the input message could be "Please help me find a nearby hotel," the set of candidate POIs may be Hotel A, Hotel B, Hotel C, etc.

[0039] In block 220 , the electronic device 110 constructs first prompt information based on the input message and a set of candidate results.

[0040] In some embodiments, the first prompt information may be any appropriate type of information used to guide the target model on how to generate target results and determine how many target results to use, what type of target results to use, etc. As an example, the first prompt information also indicates the number of at least one target result to be determined. For example, the first prompt information may be "Assume that you are an intelligent local life search engine. Your task is to understand and consider the user's search requirements to select three points of interest that best meet the user's needs from a large number of candidate POIs."

[0041] In box 230, the electronic device 110 provides first prompt information to the target model to determine at least one target result from a set of candidate results, and the target model is fine-tuned based on a set of sample requests and annotation information, and the annotation information indicates the ranking results of a set of sample results corresponding to the corresponding sample requests.

[0042] In some embodiments, the number of sample requests in a group can be set as needed. For each sample request, the sample request may include, but is not limited to, input information from the sample user. In some embodiments, the annotation information indicates the ranking result of a group of sample results corresponding to the corresponding sample request. For example, for a sample request of "Please recommend a hotel for me," the corresponding annotation information may indicate the ranking result of a group of hotels corresponding to this sample request. As an example, the electronic device may sort hotels by price, rating, distance, etc., and obtain the final ranking result as Hotel A, Hotel B, and Hotel C.

[0043] The following describes the process of obtaining a set of sample requests.

[0044] In some embodiments, a set of sample requests may include a first sample request. The electronic device may obtain a first set of sample results corresponding to the first sample request. The sample results may be a set of sample interest points determined for the first sample request.

[0045] As an example, the electronic device may use the service module and the first sample request to determine a set of sample results, that is, the electronic device may input the first sample request into the service module to obtain a set of sample results output by the service module.

[0046] As another example, a set of sample results corresponding to the first sample request may also be synthesized by a synthesis model.

[0047] As an example, referring to FIG3A , in box 310 , the electronic device may synthesize the candidate store, candidate prompt information, etc. corresponding to the user request based on the synthesis model to construct unlabeled data for subsequent model processing.

[0048] In some embodiments, the service module may be any appropriate model for generating sample results based on a request, and the model may be a deep learning model or a deep learning network, etc.

[0049] In some embodiments, the first sample request may include a sample request obtained from a real dataset and / or a sample request constructed based on a synthetic dataset. The real dataset may represent real sample requests generated by sample users during historical request processes. For example, if user A entered the request "Please help me find a shopping mall near location A" one year ago, user A may be used as a sample user, and the request entered by user A may be used as a sample request in the real dataset.

[0050] In some embodiments, the electronic device may determine first evaluation information of the first set of sample results. The first evaluation information may be used to represent a score corresponding to each sample interest point in the first set of sample results.

[0051] As an example, the electronic device may determine to provide a first set of sample results and first reference information to the first model, where the first reference information describes conditions corresponding to a set of preset evaluation results, such as the evaluation rules used to determine the first evaluation information corresponding to this set of sample results. As an example, if the electronic device determines that the intent corresponding to the first sample request is clear and the constraints corresponding to the sample results indicated by the first sample request are clear, then the electronic device may set the evaluation information corresponding to sample results that do not meet the intent or the constraints to 0.

[0052] In some embodiments, the electronic device may determine first evaluation information of the first set of sample results based on an output result of the first model. The output result may be candidate evaluation information corresponding to the first set of sample results determined by the first model.

[0053] As an example, referring to Figure 3A, in box 320, the electronic device can determine the output result of the first model (candidate evaluation information) as the first evaluation information corresponding to the first group of sample results. Such first evaluation information can be, for example, scoring information for the first group of sample results.

[0054] As another example, the electronic device can receive the target evaluation information corresponding to the first set of sample results input by the user, and determine the target evaluation information corresponding to the first set of sample results as the first evaluation information corresponding to the first set of sample results, where the target evaluation information can be generated by the user after proofreading the output results (candidate evaluation information) of the first model.

[0055] In some embodiments, the electronic device may sort a group of sample results based on the first evaluation information to determine first annotation information corresponding to the first sample request.

[0056] In some embodiments, the set of sample requests includes a target sample request. In some embodiments, the electronic device may construct the second prompt information based on the target sample request and the corresponding third set of sample results.

[0057] In some embodiments, the second reference information indicates different strategies used by the target model to determine a set of target sample results when the target sample request meets different conditions.

[0058] As an example, if the target sample request is a request related to recommended stores, the second prompt information may indicate:

[0059] If keywords such as "nearest" or "within XX kilometers" appear in the target request, the merchants with the "nearest" predetermined number will be selected first.

[0060] As another example, if the target sample request is a request related to recommended stores, the second prompt information may indicate:

[0061] If the target request contains keywords such as "high cost performance" and "good quality and low price", the merchants with the "lowest price" will be given priority.

[0062] In other embodiments, the second prompt information may also be used to instruct the target model how to select target sample results and how many target sample results to select, etc.

[0063] In some embodiments, the electronic device may provide second prompt information to the target model to obtain a set of target sample results determined by the target model from the third set of sample results.

[0064] The electronic device may fine-tune the target model based on a set of sample results and target annotation data corresponding to the target sample request. In some embodiments, the electronic device may adjust model parameters corresponding to the target model based on a comparison result of a set of sample results and target annotation data corresponding to the target sample request. The electronic device may obtain a trained target model in response to meeting predetermined training conditions, where the training conditions may include, for example, a training duration reaching a threshold or a loss function reaching a minimum.

[0065] To enhance the user experience, in some embodiments, the target model can not only output a set of target sample results, but also provide reasons for outputting a set of target sample results. For each target sample result, the reason corresponding to the target sample result can specifically include the reason why the target sample result was selected from multiple sample results or the advantages of the target sample result, etc.

[0066] At block 240 , the electronic device 110 generates a response to the input message based on the at least one target result.

[0067] In some embodiments, the response may be any appropriate type of response, such as a voice type response, a text type response, and the like.

[0068] In summary, referring to Figure 3B, in block 330, the electronic device may obtain a trained target model based on continuous training and evaluation of the target model to be trained. In block 340, the electronic device may generate a response to the input message based on the trained target model and at least one target result.

[0069] In this way, the embodiments of the present disclosure can more accurately understand the user's intention, improve the accuracy and efficiency of recommending points of interest, and enhance the user's search experience.

[0070] Example devices and equipment

[0071] Embodiments of the present disclosure also provide corresponding apparatuses for implementing the above-described methods or processes. FIG4 shows a schematic structural block diagram of an exemplary information processing apparatus 400 according to certain embodiments of the present disclosure. Apparatus 400 may be implemented as or included in electronic device 110. Each module / component in apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0072] As shown in Figure 4, the device 400 includes a determination module 410, which is configured to determine a set of candidate results that match the input message in response to receiving an input message; a construction module 420, which is configured to construct first prompt information based on the input message and the set of candidate results; a processing module 430, which is configured to provide the first prompt information to the target model to determine at least one target result from a set of candidate results, the target model is fine-tuned based on a set of sample requests and annotation information, the annotation information indicates a sorting result of a set of sample results corresponding to the corresponding sample request; and a generation module 440, which is configured to generate a response to the input message based on at least one target result.

[0073] In some embodiments, the first prompt information further indicates the number of at least one target result to be determined.

[0074] In some embodiments, a group of sample requests includes a first sample request, and the device 400 also includes a sample processing module, which is configured to obtain a first group of sample results corresponding to the first sample request; determine first evaluation information of the first group of sample results; and sort a group of sample results based on the first evaluation information to determine first annotation information corresponding to the first sample request.

[0075] In some embodiments, the sample processing module is further configured to provide a first set of sample results and first reference information to the first model, wherein the first reference information describes conditions corresponding to a set of preset evaluation results; and determine first evaluation information of the first set of sample results based on the output results of the first model.

[0076] In some embodiments, the first sample request includes: a sample request obtained from a real data set, and / or a sample request constructed based on a synthetic data set, and the first set of sample results includes: a set of sample results determined based on the first sample request using a service module; or a synthesized set of sample results.

[0077] In some embodiments, the set of sample requests includes a synthesized second sample request, and the second annotation information associated with the second sample request is determined based on a ranking result of the synthesized second set of sample results.

[0078] In some embodiments, a group of sample requests includes a target sample request, and the device 400 also includes a result acquisition module, which is configured to construct a second prompt information based on the target sample request and the corresponding third group of sample results; provide the second prompt information to the target model to obtain a group of target sample results determined by the target model from the third group of sample results; and fine-tune the target model based on a group of sample results and target annotation data corresponding to the target sample request.

[0079] In some embodiments, the second prompt information further includes second reference information, where the second reference information indicates different strategies used by the target model to determine a set of target sample results when the target sample request meets different conditions.

[0080] In some embodiments, the target model also provides a rationale for outputting a set of target sample results.

[0081] In some embodiments, the input message indicates a retrieval request for a point of interest, and the at least one target result includes at least one point of interest that matches the retrieval request.

[0082] The modules included in the device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the modules in the device 400 can be implemented at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0083] FIG5 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 500 shown in FIG5 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 500 shown in FIG5 can be used to implement the electronic device 110 of FIG1 .

[0084] As shown in FIG5 , electronic device 500 is a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processing unit 510 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 500.

[0085] The electronic device 500 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 500.

[0086] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 5 , a disk drive for reading from or writing to a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0087] The communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0088] Input device 550 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 560 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 500 may also communicate with one or more external devices (not shown) via communication unit 540 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with electronic device 500, or with any device that allows electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0089] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0090] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0091] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0092] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0093] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0094] While various implementations of the present disclosure have been described above, the above descriptions are intended to be illustrative, non-exhaustive, and non-limiting to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method, comprising: In response to receiving an input message, determining a set of candidate results that match the input message; Constructing first prompt information based on the input message and the set of candidate results; providing the first hint information to a target model to determine at least one target result from the set of candidate results, the target model being fine-tuned based on a set of sample requests and annotation information indicating a ranking result of a set of sample results corresponding to the corresponding sample requests; as well as A response to the input message is generated based on the at least one target result. 2 . The method according to claim 1 , wherein the first prompt information further indicates the number of the at least one target result to be determined.

3. The method of claim 1 , wherein the set of sample requests comprises a first sample request, the method further comprising: Obtaining a first set of sample results corresponding to the first sample request; Determining first evaluation information of the first group of sample results; as well as Based on the first evaluation information, the set of sample results is sorted to determine first annotation information corresponding to the first sample request.

4. The method according to claim 3, wherein determining the first evaluation information of the set of sample results comprises: providing the first set of sample results and first reference information to a first model, the first reference information describing conditions corresponding to a set of preset evaluation results; as well as Based on the output results of the first model, the first evaluation information of the first group of sample results is determined.

5. The method of claim 3, wherein the first sample request comprises: Sample requests taken from real datasets, and / or sample requests constructed based on synthetic datasets, The first set of sample results includes: using a service module to request based on the first sample A determined set of sample results; or, a synthetic set of sample results. 6 . The method according to claim 1 , wherein the set of sample requests comprises a synthesized second sample request, and the second annotation information associated with the second sample request is determined based on a ranking result of the synthesized second set of sample results.

7. The method of claim 1, wherein the set of sample requests comprises a target sample request, the method further comprising: Constructing second prompt information based on the target sample request and the corresponding third group of sample results; providing the second prompt information to the target model to obtain a set of target sample results determined by the target model from the third set of sample results; as well as The target model is fine-tuned based on the set of sample results and the target annotation data corresponding to the target sample request.

8. The method according to claim 7, wherein the second prompt information further includes second reference information, and the second reference information indicates: when the target sample request meets different conditions, the target model is used to determine different strategies for the set of target sample results.

9. The method of claim 7, wherein the target model also provides reasons for outputting the set of target sample results.

10. The method of claim 1, wherein the input message indicates a retrieval request for a point of interest, and the at least one target result includes at least one point of interest matching the retrieval request.

11. An information processing device, comprising: a determination module, configured to determine, in response to receiving an input message, a set of candidate results matching the input message; A construction module, configured to construct first prompt information based on the input message and the set of candidate results; a processing module configured to provide the first prompt information to a target model to determine at least one target result from the set of candidate results, the target model being fine-tuned based on a set of sample requests and annotation information, the annotation information indicating a ranking result of a set of sample results corresponding to the corresponding sample request; as well as The generating module is configured to generate a response to the input message based on the at least one target result.

12. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 10.

Images