Training sample construction method, device, electronic device and readable storage medium

Abstract

The present disclosure provides a method, device, electronic device and readable storage medium for constructing a training sample, which relates to technical fields such as intelligent transportation and deep learning. The method for constructing a training sample includes: obtaining a set of travel plans; obtaining an operation information set of each travel plan set based on the operation information of each travel plan in the corresponding travel plan set; obtaining an estimation model using the operation information sets of multiple first travel plan sets and the actual travel plans in the multiple first travel plan sets; inputting the operation information sets of multiple second travel plan sets into the estimation model to obtain the actual travel plan prediction results output by the estimation model for each second travel plan set; obtaining the construction results of the training sample based on the multiple second travel plan sets and the actual travel plan prediction results of the multiple second travel plan sets. The present disclosure can reduce the construction cost of the training sample and improve the construction efficiency and accuracy of the training sample.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to artificial intelligence technologies such as intelligent transportation and deep learning. A method, apparatus, electronic device, and readable storage medium for constructing training samples are provided. Background Art

[0002] With the rapid development of artificial intelligence technologies like deep learning, LTR (learning to rank) models are playing an increasingly important role in search and recommendation systems. Travel planning, a core capability of map applications, is also seeing widespread application of LTR models.

[0003] Constructing training samples is the key to using the LTR model. How to construct training samples efficiently and accurately is crucial for the LTR model. Summary of the Invention

[0004] According to a first aspect of the present disclosure, a method for constructing a training sample is provided, including: obtaining a travel plan set, wherein the travel plan set includes multiple first travel plan sets and multiple second travel plan sets, and the first travel plan set includes actual travel plans; obtaining an operation information set of each travel plan set based on operation information corresponding to each travel plan in the travel plan set; obtaining an estimation model using the operation information sets of the multiple first travel plan sets and the actual travel plans in the multiple first travel plan sets; inputting the operation information sets of the multiple second travel plan sets into the estimation model to obtain actual travel plan prediction results output by the estimation model for each second travel plan set; obtaining a construction result of the training sample based on the multiple second travel plan sets and the actual travel plan prediction results of the multiple second travel plan sets.

[0005] According to the second aspect of the present disclosure, a device for constructing a training sample is provided, including: an acquisition unit for acquiring a travel plan set, wherein the travel plan set includes multiple first travel plan sets and multiple second travel plan sets, and the first travel plan set includes actual travel plans; a processing unit for obtaining an operation information set of each travel plan set based on the operation information corresponding to each travel plan in the travel plan set; a training unit for obtaining an estimation model using the operation information sets of the multiple first travel plan sets and the actual travel plans in the multiple first travel plan sets; a prediction unit for inputting the operation information sets of the multiple second travel plan sets into the estimation model to obtain an actual travel plan prediction result output by the estimation model for each second travel plan set; and a construction unit for obtaining a construction result of the training sample based on the multiple second travel plan sets and the actual travel plan prediction results of the multiple second travel plan sets.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described above.

[0007] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method as described above.

[0008] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method described above when executed by a processor.

[0009] It can be seen from the above technical solutions that the present disclosure uses the operation information corresponding to the travel plan to complete the construction of training samples, which reduces the cost of training sample construction and improves the accuracy and efficiency of training sample construction.

[0010] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0013] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0014] Figure 3 It is a block diagram of an electronic device used to implement the method for constructing training samples according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, and various details of the embodiments of the present disclosure are included to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and mechanisms are omitted in the following description.

[0016] The method for constructing training samples disclosed in the present invention, after obtaining a travel plan set including multiple first travel plan sets and multiple second travel plan sets, first obtains an operation information set of each travel plan set based on the operation information of each travel plan in the corresponding travel plan set, then uses the operation information sets of multiple first travel plan sets and the actual travel plans of multiple first travel plans to obtain an estimation model, inputs the operation information sets of multiple second travel plan sets into the estimation model, obtains the actual travel plan prediction results output by the estimation model for each second travel plan set, and finally obtains the construction results of the training samples based on the second travel plan sets and the actual travel plan prediction results. The present invention uses the operation information corresponding to the travel plan to complete the construction of the training samples, reduces the cost of training sample construction, and improves the accuracy and efficiency of training sample construction.

[0017] Figure 1 Schematic diagram of the first embodiment of the present disclosure. Figure 1 As shown, the method for constructing training samples in this embodiment specifically includes the following steps:

[0018] S101. Acquire a travel plan set, where the travel plan set includes multiple first travel plan sets and multiple second travel plan sets, and the first travel plan set includes an actual travel plan.

[0019] When executing S101, this embodiment can obtain a travel plan set based on the log data of the client. Each travel plan set in this embodiment corresponds to a travel plan initiated by the client, and each travel plan set contains at least one travel plan.

[0020] For example, if the client initiates a travel plan from location A to location B, and if the planned travel plans are travel plan 1, travel plan 2, and travel plan 3, then this embodiment will form travel plan 1, travel plan 2, and travel plan 3 into a travel plan set.

[0021] In actual application scenarios, after initiating travel planning based on public transportation, the client may not use the planned travel plan for navigation, but may only focus on the bus and / or subway stations involved in the travel plan.

[0022] If the client selects a planned travel plan for navigation, this embodiment uses the travel plan selected by the client as the actual travel plan in the travel plan set, and uses the travel plan set as the first travel plan set.

[0023] Therefore, the travel plan sets obtained by executing S101 in this embodiment include two types. The first travel plan set is a travel plan set in which the client selects an actual travel plan for navigation, and the second travel plan set is a travel plan set in which the client does not select an actual travel plan for navigation.

[0024] For example, if the travel plan set includes travel plan 1, travel plan 2, and travel plan 3, if the client selects travel plan 2 for navigation, then the travel plan set is the first travel plan set, and travel plan 2 is the actual travel plan.

[0025] S102 : Obtain an operation information set for each travel plan set according to the operation information corresponding to each travel plan in the travel plan set.

[0026] In this embodiment, after executing S101 to obtain a travel solution set including multiple first travel solution sets and multiple second travel solution sets, executing S102 to obtain an operation information set for each travel solution set based on the operation information of each travel solution in the corresponding travel solution set.

[0027] When executing S102, this embodiment can obtain the client's operations on each travel plan in the travel plan set based on the client's log data. The operation information in this embodiment includes browsing, sliding, clicking, collecting, screenshots and other operations on the travel plan.

[0028] Since different travel solution sets correspond to different travel plans, each operation information set obtained by executing S102 in this embodiment also corresponds to a different travel plan.

[0029] Specifically, when executing S102 in this embodiment to obtain the operation information set of each travel plan set based on the operation information of each travel plan in the corresponding travel plan set, an optional implementation method that can be adopted is: for each travel plan set, obtain the operation information corresponding to each travel plan in the travel plan set; sort the obtained operation information according to the timestamp; and use the sorting result of the operation information as the operation information set of the travel plan set.

[0030] That is to say, this embodiment uses the sorting result of the operation information obtained according to the timestamp as the operation information set of the travel plan set, that is, the operation information set contains multiple operation information arranged in chronological order, so that the obtained operation information has a time attribute, which is used to judge whether the operation information set is reasonable.

[0031] Since the operation information recorded in the log data may be lost, the operation information in the obtained operation information set may not be complete. In order to improve the accuracy of the obtained operation information set, this embodiment may also include the following content when executing S102 to obtain the operation information set of each travel plan set: obtaining the preset operation logic, such as the operation logic of browsing relying on clicking, the operation logic of collecting relying on browsing, etc.; for each operation information set, if it is determined that the operation information contained in the operation information set meets the preset operation logic, retain the operation information set; otherwise, discard the operation information set.

[0032] In this embodiment, when executing S102 , an operation-dependent state machine may be constructed according to a preset operation logic, and the constructed operation-dependent state machine may be used to verify the operation information set.

[0033] That is, this embodiment verifies the operation information set of the travel plan set according to the preset operation logic, so as to retain only the operation information set that passes the verification, thereby further improving the accuracy of the obtained operation information set.

[0034] S103 : Obtain an estimation model using the operation information sets of the multiple first travel plan sets and actual travel plans in the multiple first travel plan sets.

[0035] After executing S102 to obtain the operation information set of each travel solution set, this embodiment executes S103 to obtain an estimation model using the obtained operation information sets of the multiple first travel solution sets and the actual travel solutions in the multiple first travel solution sets.

[0036] Specifically, when this embodiment uses the operation information sets of multiple first travel plan sets and the actual travel plans in the multiple first travel plan sets to obtain the estimation model during execution S103, an optional implementation method that can be adopted is: inputting the operation information sets of multiple first travel plan sets into the neural network model to obtain the actual travel plan prediction results output by the neural network model for each first travel plan set; adjusting the parameters of the neural network model according to the actual travel plan prediction results of each first travel plan set and the loss function value calculated from the actual travel plan, until the neural network model converges to obtain the estimation model.

[0037] That is to say, this embodiment takes the actual travel plan in the first travel plan set as a positive sample (for example, marked as 1), and takes other travel plans in the first travel plan set as negative samples (for example, marked as 0), so that the trained estimation model can estimate the travel plans in the travel plan set that belong to the actual travel plan based on the input operation information set.

[0038] S104: Input the operation information sets of the multiple second travel plan sets into the estimation model to obtain an actual travel plan prediction result output by the estimation model for each second travel plan set.

[0039] After executing S103 to obtain the estimation model, this embodiment executes S104 to input the obtained operation information sets of multiple second travel plan sets into the estimation model, thereby obtaining the actual travel plan prediction result output by the estimation model for each second travel plan set.

[0040] That is to say, this embodiment uses the estimation model obtained from the first travel plan set that includes the actual travel plan to filter out the actual travel plan prediction result from the second travel plan set that does not include the actual travel plan. The actual travel plan prediction result is the travel plan that the client is most likely to use for navigation in the second travel plan set.

[0041] S105 . Obtain a construction result of a training sample according to the multiple second travel plan sets and actual travel plan prediction results of the multiple second travel plan sets.

[0042] After executing S104 to obtain the actual travel plan prediction result of each second travel plan set, this embodiment executes S105 to obtain the construction result of the training sample based on the obtained multiple second travel plan sets and the actual travel plan prediction results of the multiple second travel plan sets.

[0043] Specifically, when this embodiment executes S105 to obtain the construction result of the training sample based on the obtained multiple second travel plan sets and the actual travel plan prediction results of the multiple second travel plan sets, the optional implementation method that can be adopted is: for each second travel plan set, the travel plan in the second travel plan set corresponding to the actual travel plan prediction result is used as a positive sample, and the other travel plans in the second travel plan set are used as negative samples. For example, the travel plan corresponding to the actual travel plan prediction result and another travel plan are used to form a travel plan pair.

[0044] It is understandable that after executing S105 to obtain the construction results of the training samples, this embodiment can also use the constructed training samples to train the sorting model, so that the trained sorting model can output the score corresponding to the input travel plan based on the travel plan.

[0045] Figure 2 Schematic diagram of the second embodiment of the present disclosure. Figure 2 As shown, the training sample construction device 200 of this embodiment includes:

[0046] The acquisition unit 201 is configured to acquire a travel plan set, where the travel plan set includes a plurality of first travel plan sets and a plurality of second travel plan sets, and the first travel plan set includes an actual travel plan.

[0047] The acquisition unit 201 may acquire a travel plan set based on the client's log data; each travel plan set acquired by the acquisition unit 201 corresponds to a travel plan initiated by the client, and each travel plan set includes at least one travel plan.

[0048] In actual application scenarios, after initiating travel planning based on public transportation, the client may not use the planned travel plan for navigation, but may only focus on the bus and / or subway stations involved in the travel plan.

[0049] If the client selects the planned travel plan for navigation, the obtaining unit 201 uses the travel plan selected by the client as the actual travel plan in the travel plan set, and uses the travel plan set as the first travel plan set.

[0050] Therefore, the travel plan set obtained by the obtaining unit 201 includes two types. The first travel plan set is a travel plan set in which the client selects an actual travel plan for navigation, and the second travel plan set is a travel plan set in which the client does not select an actual travel plan for navigation.

[0051] The processing unit 202 is configured to obtain an operation information set for each travel solution set according to the operation information corresponding to each travel solution in the travel solution set.

[0052] In this embodiment, after the acquisition unit 201 acquires a travel solution set including multiple first travel solution sets and multiple second travel solution sets, the processing unit 202 obtains an operation information set for each travel solution set based on the operation information of each travel solution in the corresponding travel solution set.

[0053] The processing unit 202 can obtain the client's operations on each travel plan in the travel plan set based on the client's log data. The operation information in this embodiment includes browsing, sliding, clicking, collecting, screenshotting and other operations on the travel plan.

[0054] Since different travel solution sets correspond to different travel plans, each operation information set obtained by the processing unit 202 also corresponds to a different travel plan.

[0055] Specifically, when the processing unit 202 obtains the operation information set of each travel plan set based on the operation information of each travel plan in the corresponding travel plan set, the optional implementation method that can be adopted is: for each travel plan set, obtain the operation information corresponding to each travel plan in the travel plan set; sort the obtained operation information according to the timestamp; and use the sorting result of the operation information as the operation information set of the travel plan set.

[0056] That is to say, the processing unit 202 uses the sorting result of the operation information obtained according to the timestamp as the operation information set of the travel plan set, that is, the operation information set contains multiple operation information arranged in chronological order, so that the obtained operation information has a time attribute, which is used to judge whether the operation information set is reasonable.

[0057] Since the operation information recorded in the log data may be lost, the operation information in the obtained operation information set may not be complete. In order to improve the accuracy of the obtained operation information set, the processing unit 202 may also include the following content when obtaining the operation information set of each travel plan set: obtaining the preset operation logic; for each operation information set, if it is determined that the operation information contained in the operation information set meets the preset operation logic, retain the operation information set; otherwise, discard the operation information set.

[0058] That is, the processing unit 202 verifies the operation information set of the travel plan set according to the preset operation logic, thereby retaining only the operation information set that passes the verification, further improving the accuracy of the obtained operation information set.

[0059] The training unit 203 is configured to obtain an estimation model using the operation information sets of the multiple first travel plan sets and actual travel plans in the multiple first travel plan sets.

[0060] In this embodiment, after the processing unit 202 obtains the operation information set of each travel plan set, the training unit 203 uses the obtained operation information sets of the multiple first travel plan sets and the actual travel plans in the multiple first travel plan sets to obtain an estimation model.

[0061] Specifically, when the training unit 203 uses the operation information sets of multiple first travel plan sets and the actual travel plans in the multiple first travel plan sets to obtain the estimation model, an optional implementation method that can be adopted is: inputting the operation information sets of multiple first travel plan sets into the neural network model to obtain the actual travel plan prediction results output by the neural network model for each first travel plan set; adjusting the parameters of the neural network model according to the actual travel plan prediction results of each first travel plan set and the loss function value calculated from the actual travel plan, until the neural network model converges to obtain the estimation model.

[0062] That is to say, the training unit 203 takes the actual travel plan in the first travel plan set as a positive sample (for example, marked as 1), and takes other travel plans in the first travel plan set as negative samples (for example, marked as 0), so that the trained estimation model can estimate the travel plans in the travel plan set that belong to the actual travel plans based on the input operation information set.

[0063] The prediction unit 204 is configured to input the operation information sets of the plurality of second travel plan sets into the estimation model to obtain an actual travel plan prediction result output by the estimation model for each second travel plan set.

[0064] In this embodiment, after the training unit 203 obtains the estimation model, the prediction unit 204 inputs the obtained operation information sets of multiple second travel plan sets into the estimation model, thereby obtaining the actual travel plan prediction results output by the estimation model for each second travel plan set.

[0065] That is to say, the prediction unit 204 uses the estimation model obtained from the first travel plan set that includes the actual travel plan to filter out the actual travel plan prediction result from the second travel plan set that does not include the actual travel plan. The actual travel plan prediction result is the travel plan that the client is most likely to use for navigation in the second travel plan set.

[0066] The construction unit 205 is configured to obtain a construction result of a training sample according to the plurality of second travel plan sets and actual travel plan prediction results of the plurality of second travel plan sets.

[0067] In this embodiment, after the prediction unit 204 obtains the actual travel plan prediction result of each second travel plan set, the construction unit 205 obtains the construction result of the training sample based on the obtained multiple second travel plan sets and the actual travel plan prediction results of the multiple second travel plan sets.

[0068] Specifically, when the construction unit 205 obtains the construction result of the training sample based on the obtained multiple second travel plan sets and the actual travel plan prediction results of the multiple second travel plan sets, the optional implementation method that can be adopted is: for each second travel plan set, the travel plan in the second travel plan set corresponding to the actual travel plan prediction result is used as a positive sample, and the other travel plans in the second travel plan set are used as negative samples.

[0069] It is understandable that after obtaining the construction results of the training samples, the construction unit 205 can also use the constructed training samples to train the sorting model, so that the trained sorting model can output the score corresponding to the input travel plan based on the travel plan.

[0070] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0071] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0072] like Figure 3 , is a block diagram of an electronic device for constructing a training sample according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0073] like Figure 3As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the device 300 can also be stored in the RAM 303. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0074] Multiple components in device 300 are connected to I / O interface 305, including: input unit 306, such as a keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as a magnetic disk, optical disk, etc.; and communication unit 309, such as a network card, modem, wireless communication transceiver, etc. Communication unit 309 allows device 400 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0075] The computing unit 301 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the method for constructing a training sample. For example, in some embodiments, the method for constructing a training sample can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308.

[0076] In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method for constructing a training sample described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the method for constructing a training sample in any other appropriate manner (e.g., by means of firmware).

[0077] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0078] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable training sample construction device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0079] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0080] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0081] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0082] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship is established by computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service system that addresses the management difficulties and poor business scalability of traditional physical hosts and VPS services ("Virtual Private Servers," or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0083] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0084] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for constructing a training sample, comprising: Obtaining a travel plan set, where the travel plan set includes multiple first travel plan sets and multiple second travel plan sets, where the first travel plan sets include actual travel plans, and the second travel plan sets do not include actual travel plans, and the travel plans in the travel plan sets are used for navigation; Obtaining an operation information set for each travel plan set according to operation information corresponding to each travel plan in the travel plan set, wherein the operation information includes at least one of browsing, clicking, sliding, collecting, and screenshotting the travel plan; Obtaining an estimation model using the operation information sets of the plurality of first travel solution sets and actual travel solutions in the plurality of first travel solution sets; Inputting the operation information sets of the plurality of second travel plan sets into the estimation model to obtain an actual travel plan prediction result output by the estimation model for each second travel plan set; A construction result of a training sample is obtained according to the multiple second travel plan sets and actual travel plan prediction results of the multiple second travel plan sets.

2. The method according to claim 1, wherein The obtaining of the operation information set of each travel plan set according to the operation information corresponding to each travel plan in the travel plan set includes: For each travel plan set, obtain operation information corresponding to each travel plan in the travel plan set; Sort the obtained operation information according to the timestamp; The sorting result of the operation information is used as the operation information set of the travel plan set.

3. The method according to claim 1, wherein The operation information set for obtaining each travel plan set includes: Get the preset operation logic; For each operation information set, if it is determined that the operation information included in the operation information set meets the preset operation logic, the operation information set is retained.

4. The method according to claim 1, wherein The obtaining of the estimation model by using the operation information set of the plurality of first travel solution sets and actual travel solutions in the plurality of first travel solution sets includes: Inputting the operation information sets of the plurality of first travel plan sets into a neural network model to obtain an actual travel plan prediction result output by the neural network model for each first travel plan set; According to the actual travel plan prediction results of each first travel plan set and the loss function value calculated from the actual travel plan, the parameters of the neural network model are adjusted until the neural network model converges to obtain the estimation model.

5. The method according to claim 1, wherein The step of obtaining a construction result of a training sample based on the plurality of second travel plan sets and actual travel plan prediction results of the plurality of second travel plan sets includes: For each second travel plan set, the travel plan in the second travel plan set that corresponds to the actual travel plan prediction result is used as a positive sample, and the other travel plans in the second travel plan set are used as negative samples.

6. A device for constructing a training sample, comprising: an acquiring unit, configured to acquire a travel plan set, wherein the travel plan set includes a plurality of first travel plan sets and a plurality of second travel plan sets, wherein the first travel plan sets include actual travel plans, and the second travel plan sets do not include actual travel plans, and the travel plans in the travel plan sets are used for navigation; a processing unit configured to obtain, based on the operation information corresponding to each travel plan in the travel plan set, an operation information set for each travel plan set, wherein the operation information includes at least one of browsing, clicking, sliding, collecting, and screenshotting the travel plan; a training unit, configured to obtain an estimation model using the operation information sets of the plurality of first travel plan sets and actual travel plans in the plurality of first travel plan sets; a prediction unit, configured to input the operation information sets of the plurality of second travel plan sets into the estimation model, and obtain an actual travel plan prediction result output by the estimation model for each second travel plan set; The construction unit is configured to obtain a construction result of a training sample according to the plurality of second travel plan sets and actual travel plan prediction results of the plurality of second travel plan sets.

7. The device according to claim 6, wherein When the processing unit obtains the operation information set of each travel solution set according to the operation information corresponding to each travel solution in the travel solution set, the processing unit specifically performs: For each travel plan set, obtain operation information corresponding to each travel plan in the travel plan set; Sort the obtained operation information according to the timestamp; The sorting result of the operation information is used as the operation information set of the travel plan set.

8. The device according to claim 6, wherein When the processing unit obtains the operation information set of each travel plan set, it specifically performs the following steps: Get the preset operation logic; For each operation information set, if it is determined that the operation information included in the operation information set meets the preset operation logic, the operation information set is retained.

9. The device according to claim 6, wherein When the training unit obtains the estimation model using the operation information set of the plurality of first travel plan sets and the actual travel plans in the plurality of first travel plan sets, the training unit specifically performs: Inputting the operation information sets of the plurality of first travel plan sets into a neural network model to obtain an actual travel plan prediction result output by the neural network model for each first travel plan set; According to the actual travel plan prediction results of each first travel plan set and the loss function value calculated from the actual travel plan, the parameters of the neural network model are adjusted until the neural network model converges to obtain the estimation model.

10. The device according to claim 6, wherein When the construction unit obtains the construction result of the training sample according to the plurality of second travel plan sets and the actual travel plan prediction results of the plurality of second travel plan sets, the construction unit specifically performs: For each second travel plan set, the travel plan in the second travel plan set that corresponds to the actual travel plan prediction result is used as a positive sample, and the other travel plans in the second travel plan set are used as negative samples.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images