Information push method, information push device, readable storage medium and electronic device

Abstract

The present disclosure relates to the field of computer technology, and provides information push methods and devices, computer-readable storage media, and electronic devices. Among them, the above method includes: obtaining the user's historical voice data, performing word segmentation processing on the text corresponding to the historical voice data; matching the word segmentation result with the keywords in the first vocabulary to determine the first target real scene; obtaining the second vocabulary associated with the first target real scene, matching the word segmentation result with the preset keywords in the second vocabulary; determining the target preset keywords that are successfully matched, and obtaining the explanation recommendation information associated with the target preset keywords; pushing the explanation recommendation information to the client corresponding to the value-added developer. Based on the processing of voice data during the online viewing process, this solution can determine the user's focus, so that the value-added developer can make explanation recommendations based on the user's focus, thereby improving the accuracy of product recommendations.

Description

Background Art

[0002] In the process of marketing and recommending products corresponding to real scenarios, for example, marketing of insurance products related to retirement communities, marketing of insurance products related to rehabilitation hospitals, etc., allowing users to actually experience or visit real scenes, and recommending and explaining products to users during the visit and experience has become a key marketing link, which plays a vital role in improving users' purchasing experience.

[0003] Taking the recommendation and explanation of retirement community-related insurance as an example, the relevant technology mainly uses offline tours to allow users to have a sightseeing experience of the retirement community, so as to achieve the purpose of marketing the retirement community insurance.

[0004] However, this method of direct offline viewing lacks differentiation and pertinence for different users, and cannot provide users with accurate explanation information and tour information, so that users cannot accurately obtain information corresponding to the product, affecting the accuracy of users' acquisition of product information. In addition, this method of direct offline viewing, due to its lack of pertinence, will also affect the efficiency of users in obtaining product information to a certain extent.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The purpose of the present disclosure is to provide an information push method, an information push device, a computer-readable storage medium and an electronic device, thereby improving, at least to a certain extent, the existing problem of low accuracy and low efficiency in the recommendation and explanation of products related to real scenarios.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to a first aspect of the present disclosure, there is provided an information push method, comprising: obtaining historical voice data of a user, performing word segmentation processing on a text corresponding to the historical voice data; matching the word segmentation result with keywords in a first vocabulary to determine a first target real scene corresponding to the historical voice data, wherein the first vocabulary includes keywords for characterizing different real scenes; obtaining a second vocabulary associated with the first target real scene, matching the word segmentation result of the text corresponding to the historical voice data with preset keywords in the second vocabulary; determining a successfully matched target preset keyword in the second vocabulary, and obtaining explanation recommendation information associated with the target preset keyword; pushing the explanation recommendation information to a client corresponding to a value-added developer, so that the value-added developer explains the first target real scene to the user offline according to the explanation recommendation information; wherein the historical voice data is determined based on the communication voice when the value-added developer assists the user in experiencing virtual reality scenes corresponding to different real scenes online.

[0009] In an exemplary embodiment of the present disclosure, based on the aforementioned solution, the explanation recommendation information includes one or more of the explanation words, promotional pictures, and promotional videos associated with the target preset keywords.

[0010] In an exemplary embodiment of the present disclosure, based on the aforementioned scheme, the acquiring of the user's historical voice data and the performing of word segmentation processing on the text corresponding to the historical voice data include: acquiring the user's historical behavior data, the historical behavior data being determined based on the user's interactive operations when experiencing virtual reality scenes corresponding to different real scenes online; based on the historical behavior data, counting the total number of interactive operations performed by the user to determine the user category of the user based on the total number of interactive operations; when the user category is the target user category, acquiring the user's historical voice data and performing word segmentation processing on the text corresponding to the historical voice data.

[0011] In an exemplary embodiment of the present disclosure, based on the aforementioned scheme, after determining the first target real scene corresponding to the historical voice data, the method also includes: inputting the text corresponding to the historical voice data into a sentiment analysis model to determine the target emotion category corresponding to the historical voice data; when the target emotion category represents that the user is interested in the first target real scene, pushing an identifier of the first target real scene to the client of the value-added developer, so that the value-added developer can determine the first target real scene as the first offline explanation object according to the identifier.

[0012] In an exemplary embodiment of the present disclosure, based on the aforementioned scheme, the method also includes: obtaining historical behavior data of the user, wherein the historical behavior data is determined based on interactive operations performed by the user when experiencing virtual reality scenes corresponding to different real scenes online; determining a second target real scene that the user is interested in among the different real scenes based on the historical behavior data; pushing an identifier of the second target real scene to the client of the value-added developer, so that the value-added developer can determine the second target real scene as a second offline explanation object based on the identifier; wherein the interactive operations include one or more of clicks, drags, zooms, and slides performed by the user when experiencing virtual reality scenes corresponding to different real scenes online.

[0013] In an exemplary embodiment of the present disclosure, based on the aforementioned scheme, determining the second target real scene that the user is interested in among the different real scenes based on the historical behavior data includes: determining the number of times the user performs interactive operations on each virtual reality scene respectively; sorting the number of interactive operations in descending order, and determining that the real scenes corresponding to the first N virtual reality scenes are the second target real scenes.

[0014] In an exemplary embodiment of the present disclosure, based on the aforementioned scheme, determining the second target real scene that the user is interested in among the different real scenes based on the historical behavior data includes: determining the browsing time of each virtual reality scene by the user based on the historical behavior data; and determining the second target real scene according to the life scene corresponding to the virtual reality scene whose browsing time is greater than a preset value.

[0015] According to a second aspect of the present disclosure, there is provided an information push device, comprising:

[0016] A word segmentation processing module, which obtains the user's historical voice data and performs word segmentation processing on the text corresponding to the historical voice data;

[0017] A first target real scene determination module is configured to match the word segmentation result with keywords in a first word library to determine a first target real scene corresponding to the historical voice data, wherein the first word library includes keywords for indicating different real scenes;

[0018] A preset keyword matching module is configured to obtain a second word library corresponding to the first target real scene, and match the word segmentation result of the text corresponding to the historical voice data with the preset keywords in the second word library;

[0019] An information acquisition module is configured to determine a target preset keyword that is successfully matched in the second vocabulary, and acquire explanation recommendation information associated with the target preset keyword;

[0020] An information push module is configured to push the explanation recommendation information to a client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information;

[0021] The historical voice data is determined based on the communication voice when the value-added developer assists the user in experiencing online virtual reality scenes corresponding to different real scenes.

[0022] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the information push method as described in the first aspect of the above embodiment is implemented.

[0023] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the information push method as described in the first aspect of the above embodiment.

[0024] It can be seen from the above technical solutions that the information push method, information push device, and computer-readable storage medium and electronic device implementing the information push method in the exemplary embodiments of the present disclosure have at least the following advantages and positive effects:

[0025] In the technical solutions provided in some embodiments of the present disclosure, first, historical voice data generated in the process of communicating with value-added developers when users experience virtual reality scenes corresponding to different real scenes online is obtained; then, the historical voice data is segmented, and the segmentation results are matched with keywords in a first vocabulary to determine the first target real scene corresponding to the historical voice data; secondly, a second vocabulary associated with the first target real scene is obtained, and the segmentation results of the historical voice data are matched with preset keywords in the second vocabulary to determine the target preset keywords that are successfully matched in the second vocabulary, thereby obtaining explanation recommendation information associated with the target preset keywords, and then the explanation recommendation information can be pushed to the client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information. Compared with the related art, on the one hand, the present disclosure can determine the user's focus by analyzing and processing the voice data generated during the online viewing process, and thus push explanation recommendation information related to the user's focus to the client of the value-added developer, so that the value-added developer can give targeted explanations to the user's focus offline according to the pushed explanation recommendation information, thereby enabling the user to accurately obtain information related to the product, thereby improving the accuracy of the user's acquisition of product information; on the other hand, the present disclosure can realize the online viewing experience of products corresponding to the real scene through virtual reality technology, thereby reducing the viewing cost of products corresponding to the real scene, and because the product explanations to users are more targeted, the efficiency of users in obtaining product information corresponding to the real scene can be improved.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0028] Figure 1 A schematic diagram showing a flow chart of an information push method in an exemplary embodiment of the present disclosure;

[0029] Figure 2 A schematic diagram showing a flow chart of a method for determining a user category in an exemplary embodiment of the present disclosure;

[0030] Figure 3A schematic flow chart showing a method for determining an offline explanation object in an exemplary embodiment of the present disclosure;

[0031] Figure 4 A flowchart showing another method for determining an offline explanation object in an exemplary embodiment of the present disclosure is shown;

[0032] Figure 5 A flowchart showing a method for recommending and explaining a retirement community based on a virtual reality scene in an exemplary embodiment of the present disclosure is shown;

[0033] Figure 6 A schematic diagram showing the structure of an information push device in an exemplary embodiment of the present disclosure is shown;

[0034] Figure 7 A schematic diagram showing the structure of a computer storage medium in an exemplary embodiment of the present disclosure; and

[0035] Figure 8 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0036] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0037] The terms "a", "an", "the" and "said" are used in this specification to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first" and "second" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0038] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

[0039] Nowadays, in the process of marketing products corresponding to real scenarios, for example, marketing of insurance products related to retirement communities, marketing of insurance products related to rehabilitation hospitals, etc., allowing users to actually experience or visit real scenes, and explaining the products to users during the user experience and sightseeing process has become a key marketing link, which plays a vital role in improving users' purchasing experience.

[0040] Taking the recommendation and explanation of insurance related to retirement communities as an example, in one related technology, users are mainly allowed to experience the housing security, medical equipment, community activities, etc. of retirement communities through direct offline viewing. Specifically, the value-added developers, namely insurance agents, lead users to the retirement community base for actual experience and explanation, so as to achieve the purpose of marketing retirement community insurance; in another related technology, insurance agents directly visit customers to make relevant recommendations and explanations on retirement community insurance.

[0041] However, the offline viewing method lacks differentiation and pertinence for different users, and cannot provide users with accurate explanation information, so that users cannot accurately obtain information corresponding to the product, affecting the accuracy of users' acquisition of product information. In addition, this offline viewing method, due to its lack of pertinence, will affect the efficiency of users in obtaining product information to a certain extent. . The method of directly visiting customers to explain and recommend retirement community insurance has limited graphic and text display effects, cannot bring customers a real retirement community experience, and the time cost of visiting customers is high.

[0042] In the embodiments of the present disclosure, firstly, an information push method is provided, which overcomes the defects existing in the above-mentioned related technologies at least to a certain extent.

[0043] Figure 1 FIG. 1 is a flow chart showing a method for pushing information in an exemplary embodiment of the present disclosure. Figure 1 , the method comprising:

[0044] Step S110, obtaining historical voice data of the user, and performing word segmentation processing on the text corresponding to the historical voice data;

[0045] Step S120, matching the word segmentation result with keywords in a first vocabulary to determine a first target real scene corresponding to the historical voice data, wherein the first vocabulary includes keywords for representing different real scenes;

[0046] Step S130, obtaining a second word library associated with the first target real scene, and matching the word segmentation result of the text corresponding to the historical voice data with the preset keywords in the second word library;

[0047] Step S140, determining a target preset keyword that has been successfully matched in the second vocabulary, and obtaining explanation recommendation information associated with the target preset keyword;

[0048] Step S150, pushing the explanation recommendation information to the client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information;

[0049] The historical voice data is determined based on the communication voice when the value-added developer assists the user in experiencing online virtual reality scenes corresponding to different real scenes.

[0050] exist Figure 1In the technical solution provided by the illustrated embodiment, first, historical voice data generated in the process of communicating with value-added developers when users experience virtual reality scenes corresponding to different real scenes online is obtained; then, the historical voice data is segmented, and the segmentation results are matched with keywords in a first vocabulary to determine the first target real scene corresponding to the historical voice data; secondly, a second vocabulary associated with the first target real scene is obtained, and the segmentation results of the historical voice data are matched with preset keywords in the second vocabulary to determine the target preset keywords that are successfully matched in the second vocabulary, thereby obtaining explanation recommendation information associated with the target preset keywords, and then the explanation recommendation information can be pushed to the client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information. Compared with the related art, on the one hand, the present disclosure can determine the user's focus by analyzing and processing the voice data generated during the online viewing process, and thus push explanation recommendation information related to the user's focus to the client of the value-added developer, so that the value-added developer can give targeted explanations to the user's focus offline according to the pushed explanation recommendation information, thereby enabling the user to accurately obtain information related to the product, thereby improving the accuracy of the user's acquisition of product information; on the other hand, the present disclosure can realize the online viewing experience of products corresponding to the real scene through virtual reality technology, thereby reducing the viewing cost of products corresponding to the real scene, and because the product explanations to users are more targeted, the efficiency of users in obtaining product information corresponding to the real scene can be improved.

[0051] The following Figure 1 The specific implementation methods of each step in the embodiment shown are described in detail:

[0052] In step S110, historical voice data of the user is obtained, and word segmentation processing is performed on the text corresponding to the historical voice data.

[0053] In an exemplary embodiment, the historical voice data is determined based on the communication voice when the value-added developer assists the user in experiencing online virtual reality scenes corresponding to different real scenes.

[0054] Among them, different real scenes may include real scenes related to the marketing products. For example, when marketing retirement community insurance, different real scenes may include various real life scenes in the retirement community, such as sports scenes, cultural scenes, tea garden scenes, medical scenes, etc. in the retirement community; when marketing rehabilitation hospital insurance, different real scenes may include various real scenes in the rehabilitation hospital, such as rehabilitation room scenes and physiotherapy room scenes in the rehabilitation hospital; when marketing products related to memorial gardens, such as memorial garden insurance products, different real scenes may include physical scenes corresponding to different types of memorial gardens, where memorial gardens can be understood as cemeteries and mausoleums.

[0055] Of course, different real scenarios may also include other real scenarios related to other marketing products, which is not particularly limited in this exemplary embodiment.

[0056] In the present disclosure, the specific implementation methods are explained by taking the marketing recommendation and explanation of retirement community insurance as an example. The specific implementation methods of marketing recommendation and explanation of products related to other real scenarios can refer to the specific implementation methods of marketing recommendation and explanation of insurance related to retirement communities, and will not be repeated one by one in the present disclosure.

[0057] In an exemplary scenario, virtual reality scenes corresponding to various life scenes of the retirement community can be generated based on VR (Virtual Reality) technology. In this way, before the value-added developer actually shows the user the VR scenes corresponding to various real life scenes of the retirement community online. Then, the voice data of the communication between the value-added developer and the user during the online viewing process can be obtained to analyze the user's focus based on the voice data of the communication. In this way, when the value-added developer takes the user to an actual offline experience, the user's focus can be explained in a targeted manner, which can improve the accuracy of the product information obtained by the user.

[0058] Among them, the life scenes in the retirement community can include sports scenes, social scenes, health scenes, cultural scenes, tea garden scenes, etc. Sports scenes, social scenes, health scenes, etc. can also be further subdivided. For example, the sports scene can include dance rooms, swimming pools, billiard rooms, chess and card rooms, golf rooms, gyms, bonsai gardens and other sub-scenes. Social scenes can include social areas with different themes in the retirement community, such as four-season flower halls, activity halls, gardening gardens, wind and rain corridors, classical gardens, etc. Health scenes can include body massage areas, special nursing rooms, memory towns, etc.; cultural scenes can include home theaters, open reading areas, piano rooms, handicraft exhibition rooms, libraries, calligraphy and painting rooms, flower rooms, etc., and tea garden scenes can include black tea planting and picking areas, green tea planting and picking areas, etc. A retirement community includes one or more of these various life scenes.

[0059] Exemplarily, before analyzing the user's focus, the user's category can be determined first, and after determining that the user's category is the target category, steps S110 to S150 can be performed. That is, in the present disclosure, historical voice data analysis can be performed on the target category user to determine the focus of the target category user.

[0060] In this way, the value-added developers can be assisted to select target users from all users who have online experience, provide offline viewing services to the target users, and explain the retirement community to the user based on the user's focus during the offline viewing process. This can not only achieve precise marketing for target users, but also save the time of value-added developers and the cost of offline viewing.

[0061] For example, Figure 2 A flow chart showing a method for determining a user category in an exemplary embodiment of the present disclosure is shown. Figure 2 , the method may include steps S210 to S220.

[0062] In step S210, historical behavior data of the user is obtained, where the historical behavior data is determined based on interactive operations of the user when experiencing virtual reality scenes corresponding to different real scenes online.

[0063] Exemplarily, during the online viewing process, users can also watch various virtual reality scenes according to their own needs through interactive operations, such as users can freely view the retirement community through the link shared by the value-added developer. Among them, the interactive operation may include one or more of clicking, dragging, zooming, and sliding when the user experiences the virtual reality scenes corresponding to different real scenes online. For example, taking the retirement community as an example, the user can click on the virtual reality scene corresponding to a real scene of the retirement community to enter the browsing and viewing of the virtual reality scene. During the viewing process, the user can choose to zoom in and out of a certain detail in the virtual reality scene according to his or her own needs.

[0064] In an exemplary implementation, the user's historical behavior data can be obtained through the plug-in platform. Data plug-in means that when a user triggers an action corresponding to any of the aforementioned interactive operations, the background will record which user is currently on which page and at what location to trigger the action. Therefore, taking the marketing of insurance associated with retirement communities as an example, the data plug-in platform can quickly obtain the user's interactive data when experiencing VR scenes corresponding to different real scenes in retirement communities online.

[0065] Next, in step S220, based on the historical behavior data, the total number of interactive operations performed by the user is counted to determine the user category of the user according to the total number of interactive operations.

[0066] Exemplarily, after obtaining the user's historical behavior data, the category of the current user can be determined based on the historical behavior data. For example, the historical behavior data can be statistically analyzed to determine the total number of interactive operations performed by the user in the VR platform corresponding to the retirement community. For example, continuing to take the retirement community as an example, during an online experience of the retirement community, the user clicked on the sports scene 4 times, dragged the gym in the sports scene once, clicked on the cultural scene 7 times, and enlarged the library in the cultural scene 3 times. It can be determined that the total number of interactive operations performed by the user is 4+1+7+3=15 times. Then, the user category of the user is determined based on the mapping relationship between the total number of interactive operations performed by the user and the user category.

[0067] For example, the mapping relationship between the total number of interactive operations and the user category can be pre-configured according to business needs. The mapping relationship can be used to indicate the relationship between the total number of different interactive operations and the user's interest in the retirement community. For example, it can be configured that when the total number of interactions is less than 20, the user category is the first category, when the number of interactions is greater than or equal to 20 and less than 40, the user category is the second category, and when the number of interactions is greater than or equal to 40, the user category is the third category. Among them, the first category can be used to indicate that the user has a low interest in the retirement community, the second category can be used to indicate that the user has a medium interest in the retirement community, and the third category can be used to indicate that the user has a high interest in the retirement community.

[0068] In another exemplary implementation, the total browsing time of the users for each VR scene of the retirement community can also be counted based on the acquired historical behavior data, and then the user category can be determined based on the total browsing time. For example, if the total browsing time is less than 20 minutes, it is the first category, if the total browsing time is greater than 20 minutes and less than 30 minutes, it is the second category, if the browsing time is greater than 30 minutes, it is the third category, and so on.

[0069] In another exemplary embodiment, the user category can also be determined based on the total number of interactive operations and the total browsing time, such as the user category corresponding to the user with a total number of operations greater than 30 and a total browsing time greater than 20 is the target user category, etc. This exemplary embodiment does not specifically limit this.

[0070] After determining the user category of the current user, exemplarily, the specific implementation of step S110 may be, when the user category is the target user category, obtaining the user's historical voice data, then determining the text data corresponding to the historical voice data through voice recognition technology, and performing word segmentation processing on the text data corresponding to the historical voice data.

[0071] The target user category can be understood as the third category mentioned above, that is, the target user category is used to indicate that users have a high overall interest in the retirement community. That is, users belonging to the target category can be understood as potential users or valuable users, and such users are more likely to purchase retirement community insurance.

[0072] Continue to refer Figure 1 In step S120, the word segmentation result is matched with the keywords in the first vocabulary to determine the first target real scene corresponding to the historical voice data.

[0073] In an exemplary embodiment, the first vocabulary includes keywords for characterizing different real scenes. For example, the keywords stored in the first vocabulary may include the names of sub-real scenes included in different real scenes, and an index relationship between different real scenes and the names of their corresponding sub-real scenes may be established in the first vocabulary. Taking a retirement community as an example, the first vocabulary includes keywords for characterizing different life scenes in the retirement community. For example, the keywords stored in the first vocabulary may include the names of sub-life scenes corresponding to different life scenes in the retirement community, and an index relationship between different life scenes and their corresponding sub-life scene names may be established in the first vocabulary.

[0074] For example, sports scenes can be used as indexes to store corresponding keywords such as "dance room, swimming pool, billiard room, chess and card room, golf room, gym, bonsai garden", and social scenes can be used as indexes to store corresponding keywords such as "four seasons flower hall, activity hall, horticultural garden, wind and rain corridor, classical garden".

[0075] After the text data corresponding to the historical voice data is segmented, the segmentation result can be matched with the keywords in the first vocabulary, so as to determine the first target real scene corresponding to the historical voice data based on the real scene to which the successfully matched keywords belong. Taking the elderly care community as an example, that is, by matching the segmentation result with the keywords in the first vocabulary, it can be identified which VR scene in the elderly care community the user's historical voice data refers to.

[0076] For example, when the word segmentation of the text data corresponding to the user's historical voice data contains "dance studio" or "dance hall", it can be successfully matched with "dance studio" in the first vocabulary. Through the index relationship in the first vocabulary, it can be determined that the keyword "dance studio" belongs to the sports scene, and it can be determined that the user's historical voice data is for the "sports scene" in the retirement community. In other words, when marketing products related to retirement communities, the first target real scene corresponding to the historical voice data is the sports scene in the retirement community.

[0077] Next, in step S130, a second vocabulary associated with the first target real scene is obtained, and the word segmentation result of the text corresponding to the historical voice data is matched with the preset keywords in the second vocabulary.

[0078] In an exemplary embodiment, the second word library associated with the marketing product may be pre-configured for different real scenarios associated with the marketing product.

[0079] Taking insurance marketing related to retirement communities as an example, preset keywords associated with each life scene in the retirement community can be configured in advance, so as to generate a second vocabulary associated with each life scene. Among them, preset keywords associated with each life scene can be configured according to one's own needs or experience. Preset keywords can be used to characterize issues that users are more concerned about or concerned about in this life scene. For example, a preset keyword "duration" can be configured in a sports scene, and the preset keyword "duration" can be used to characterize that users are more concerned about the opening hours or opening times of each sports venue in a sports scene. The preset keyword "pesticide" is configured in a tea garden scene, which can be used to characterize that users have higher requirements or are more concerned about the green health of food in the tea garden scene.

[0080] Exemplarily, after determining the first target real scene corresponding to the historical voice data, a second vocabulary library associated with the first target real scene can be obtained, and the word segmentation results of the text corresponding to the historical voice data can be matched with preset keywords in the second vocabulary library to determine the user's focus or content of interest in the first target real scene.

[0081] For example, taking a retirement community as an example, the text corresponding to the historical voice data contains the word "pesticide", and the first target real scene is a tea garden scene in the retirement community. This can indicate that users have higher requirements or are more concerned about the green and healthy nature of tea in the tea garden scene.

[0082] Continue to refer Figure 1 In step S140, a target preset keyword successfully matched in the second vocabulary is determined, and explanation recommendation information associated with the target preset keyword is obtained.

[0083] Exemplarily, the preset keywords corresponding to different real scenes may be configured with explanation recommendation information associated therewith in advance. The explanation recommendation information may include one or more of explanation words, promotional pictures, and promotional videos associated with the preset keywords.

[0084] Taking the retirement community as an example, the preset keywords corresponding to each life scene in the retirement community can be configured with explanation recommendation information associated with it. Among them, the preset keywords in the second vocabulary corresponding to each life scene represent the issues that users are more concerned about in this scene, and then for each preset keyword itself, the explanation words, promotional pictures, promotional videos and other explanation recommendation information in any form associated with it can be pre-configured according to the issues of concern it represents. For example, for the preset keyword "duration" in the sports scene, the opening time and opening time of each sports venue can be used as explanation words and pre-associated with the preset keyword "duration". For the preset keyword "pesticide" in the tea garden scene, the explanation words, promotional videos, promotional pictures, etc. related to the green and healthy products can be pre-associated with the preset keyword "pesticide".

[0085] For example, if a preset keyword in the second vocabulary successfully matches a segmentation result in the text corresponding to the historical voice data, the preset keyword can be used as the target preset keyword. It can also be considered that the user is more concerned about the problem represented by the target preset keyword in this scenario. For example, if the preset keyword "pesticide" in the tea garden scenario successfully matches the segmentation result in the text corresponding to the user's historical voice data, then "pesticide" can be determined as the target preset keyword. The target preset keyword "pesticide" indicates that the user is more concerned about the green health of the product, so the explanation recommendation information such as speech, promotional videos, promotional pictures, etc. that explain the green health of the product that is pre-associated with "pesticide" can be obtained.

[0086] Next, in step S150, the explanation recommendation information is pushed to the client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information.

[0087] As mentioned above, if the user's historical voice data includes a preset keyword corresponding to the first target real scene, it means that the user is more concerned about the problem corresponding to the preset keyword, so the explanation recommendation information associated with the preset keyword can be obtained, and then the explanation recommendation information can be pushed to the client of the value-added developer. In this way, the value-added developer can provide targeted and focused explanations on the user's concerns when showing the product offline based on the explanation recommendation information received by its client, thereby achieving precision marketing.

[0088] It should be noted that, in the present disclosure, online viewing can be understood as value-added developers leading users to visit and experience VR scenes of different real scenes through the VR platform, and offline viewing can be understood as value-added developers leading users to actually visit and experience the real scene base. For example, online viewing can be understood as value-added developers leading or assisting users to visit and experience the VR scenes corresponding to the retirement community through the retirement community VR platform, and offline viewing can be understood as value-added developers leading users to actually visit and experience the physical retirement community at the retirement community base.

[0089] In an exemplary embodiment, after determining the first target real scene corresponding to the historical voice data, the emotional category of the historical voice data can also be identified, and then, based on the emotional category of the historical voice data, it is determined whether the user is interested in the first target real scene, thereby determining whether to use the first target real scene object as an offline explanation object.

[0090] For example, Figure 3 A flowchart of a method for determining an offline explanation object in an exemplary embodiment of the present disclosure is shown. Figure 3 , the method may include steps S310 to S320.

[0091] In step S310, the text corresponding to the historical speech data is input into a sentiment analysis model to determine a target sentiment category corresponding to the historical speech data.

[0092] Exemplarily, a sentiment analysis model can be obtained by training sample data. The sentiment analysis model may include a sentiment classification model obtained by training a deep learning model. Specifically, the sentiment analysis model takes text data as input and takes the sentiment category corresponding to the text data as output, and is used to perform sentiment classification on the text data. The sentiment category corresponding to the sentiment analysis model may include very positive, positive, neutral, negative, very negative, and other categories. Of course, specific categories can also be configured according to one's own needs, and this exemplary embodiment does not specifically limit this.

[0093] After obtaining the sentiment analysis model, the text corresponding to the historical speech data can be input into the sentiment analysis model to determine the target sentiment category corresponding to the historical speech data based on the sentiment analysis model.

[0094] Next, in step S320, when the target emotion category represents that the user is interested in the first target real scene, the identifier of the first target real scene is pushed to the client of the value-added developer, so that the value-added developer can determine the first target real scene as the first offline explanation object according to the identifier.

[0095] Taking different real scenes in a retirement community as an example, when the target emotion category corresponding to the historical voice data is any of the very positive or positive mentioned above, it can be considered that the target emotion category represents that the user is interested in the first target real scene, and the identifier of the first target real scene can be pushed to the client of the value-added developer. In this way, after receiving the identifier, the value-added developer knows that it should determine the first target real scene as the first offline explanation object in the retirement community. In other words, when the value-added developer takes a tour offline, the first target real scene can be used as the key viewing object and explanation object, focusing on leading users to visit and experience the first target real scene, thereby improving the efficiency of users in obtaining product information.

[0096] For example, Figure 4 A flowchart showing another method for determining an offline explanation object in an exemplary embodiment of the present disclosure is shown. Figure 4 , the method may include steps S410 to S420. Wherein:

[0097] In step S410, historical behavior data of the user is obtained, where the historical behavior data is determined based on interactive operations of the user when experiencing virtual reality scenes corresponding to different real scenes online.

[0098] The historical behavior data of the user in step S410 is the same as the historical behavior data of the user mentioned in the above step S210, and will not be described again here.

[0099] Next, in step S420, based on the historical behavior data, a second target real scene that the user is interested in among the different real scenes is determined.

[0100] In an exemplary implementation, step S420 may be implemented by the following process: determining the number of times the user performs interactive operations on each virtual reality scene; sorting the number of interactive operations in descending order, and determining that the real scene corresponding to the virtual reality scenes ranked in the top N in terms of the number of interactive operations is the second target real scene. Wherein, N is a positive integer, and the specific value of N can be determined according to demand, and N is less than the number of different real scenes. Taking the different real scenes as different life scenes in a retirement community as an example, N is less than the number of life scenes included in the retirement community.

[0101] Exemplarily, after determining the number of times the user performs interactive operations on each virtual reality scene, the real scene corresponding to the virtual reality scene with the number of interactive operations greater than a preset value may be determined as the second target real scene. The preset value may be customized according to requirements.

[0102] In another exemplary embodiment, step S420 may be implemented through the following process: based on the historical behavior data, determining the browsing time of each virtual reality scene by the user; and determining the second target real scene according to the real scene corresponding to the virtual reality scene whose browsing time is greater than a preset value.

[0103] For example, taking a retirement community as an example, based on the user's historical behavior data, the total time the user browses each VR scene in the retirement community is counted, and then the life scene corresponding to the virtual reality scene with a browsing time greater than a preset value is determined as the second target real scene.

[0104] Exemplarily, after determining the browsing time of each virtual reality scene by the user based on the historical behavior data, the browsing time can also be sorted in descending order, and the real scene corresponding to the virtual reality scenes ranked in the top M in browsing time is determined as the second target real scene. Wherein, M is also a positive integer, and the specific value of M can be determined according to demand, and M is less than the number of different real scenes. Taking the different real scenes as different life scenes in the retirement community as an example, M is less than the number of life scenes included in the retirement community.

[0105] After determining the second target real scene, in step S430, the identifier of the second target real scene is pushed to the client of the value-added developer, so that the value-added developer can determine the second target real scene as the second offline explanation object according to the identifier.

[0106] Taking the retirement community as an example, the second target real scene determined in the above step S420 is determined based on the user's historical behavior data. In other words, the user's historical behavior data can be used to analyze which life scenes in the retirement community the user is more interested in, and the identifier of the life scene can be pushed to the client of the value-added developer corresponding to the user, so that the value-added developer can determine the life scene corresponding to the identifier as the focus of the explanation in the retirement community when conducting offline explanations of the retirement community based on the identifier. In this way, the explanation can be focused on the user's concerns, improving the accuracy and efficiency of retirement community insurance marketing.

[0107] In an exemplary implementation, the offline explanation object may also be determined based on the virtual reality scene corresponding to the target interaction operation in the user's interaction operation, wherein the target interaction operation may include a zoom operation.

[0108] Continuing with the example of a retirement community, for example, when a user is touring the sports field scene in the retirement community, he or she zooms in to view the badminton court in the sports scene. It can be analyzed that the user is interested in the badminton court in the sports scene in the retirement community, and the badminton sub-scene in the sports scene can be identified as the third offline explanation object.

[0109] In another exemplary scenario, taking a retirement community as an example, users can freely view VR scenes corresponding to various life scenes in the retirement community through links shared by value-added developers, and analyze the interactive operation data when users view VR scenes in the retirement community to obtain the life scenes that users are concerned about in the retirement community. In this way, when the value-added developer explains the community through the VR viewing function, he can focus on explaining specific scenes based on the user preference scene data pushed to its client, so that users have a deep understanding of the scenes they are concerned about, thereby achieving precision marketing. In other words, the above-mentioned based Figure 4 The explanation object determined in the manner shown can also be used as the online explanation object corresponding to the VR viewing function.

[0110] In the present disclosure, taking the marketing of insurance products associated with different real-life scenarios as an example, it is possible to analyze whether a user is a target user based on the interactive data of the user experiencing VR scenarios of different real-life scenarios online, so that the value-added developer, that is, the insurance agent, can continue to communicate and exchange with the target user in depth offline, convert the target user into a policy customer, and improve the accuracy of insurance marketing. At the same time, based on the analysis of multiple dimensions such as the interactive data and voice data when the user experiences different real-life scenarios online, the user's focus can be determined, and the information related to the user's focus can be pushed to the corresponding insurance agent, and the auxiliary insurance agent can explain different key points to different customers based on the focus of different customers, which improves the accuracy of marketing, saves the time of insurance agents and customers, and improves marketing efficiency.

[0111] Next, Figure 5 A flowchart of a method for recommending a retirement community based on a virtual reality scene in an exemplary embodiment of the present disclosure is shown. Figure 5 , the method may include steps S510 to S530. Wherein:

[0112] In step S510, user data is collected; in step S520, the user data is analyzed and processed to determine the user's focus; in step S530, the user's focus is pushed to the client corresponding to the value-added developer.

[0113] Among them, the user data collected in step S510 may include user voice data, the length of time the user stays in each VR scene, the user's interactive operation data with each VR scene, etc. For the user voice data, in step S5201, the user voice data can be identified and pre-processed, and in step S5202, the keywords that the user is concerned about are extracted; for the length of time the user stays in each VR scene, in step S5203, the length of time the user stays in each VR scene is analyzed and counted, and in step S5204, the VR scene that the user is concerned about is determined; for the interactive operation data between the user and each VR scene, in step S5205, the user interactive operation data is analyzed and processed; in step S5206, the user's focus is determined. Then, the user's focus content determined in steps S5202, 5204, and 5206 is summarized and sent to the client corresponding to the value-added developer. The value-added developer may extract useful user data based on the received user's concerns in step S5301, sort out the user data in step S5302, and explain the key points in step S5303.

[0114] For example, taking the insurance marketing recommendation explanation of the retirement community as an example, the voice data transmitted by the user through the mobile app (Application) corresponding to the VR scene of the retirement community, the stay time data of each VR scene, and the interaction data of each VR scene page, such as drag and drop, sliding, clicking and other interaction data, can be collected. For voice data, the user's voice is analyzed and processed through the voice analysis program to analyze the user's emotions and keywords in different scenes. The user's focus is analyzed based on emotions and keywords; for the user's scene stay time data, the user's stay time in each scene is statistically analyzed through statistical analysis to extract the life scenes that the user is concerned about in the retirement community; for the user's interaction data on each VR scene page, the user's focus and details are obtained by collecting the user's drag and drop, sliding, clicking and other data on each VR scene page. Push the user's focus, details and other information to the client where the value-added developer is located.

[0115] Then, the target users are preliminarily screened out based on data such as the length of time users stay on the mobile APP and the number of interactions. The value-added developers can then conduct subsequent in-depth communication with the target users to convert them into policy customers. At the same time, during the in-depth communication process, the value-added developers can provide targeted and focused explanations to different customers based on data such as the users' concerns and details of interest.

[0116] Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present invention are performed. The program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk.

[0117] In addition, it should be noted that the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0118] Figure 6 The schematic diagram of the structure of the information push device in the exemplary embodiment of the present disclosure is shown. The information push device 600 may include a word segmentation processing module 610, a first target real scene determination module 620, a preset keyword matching module 630, an information acquisition module 640, and an information push module 650. Among them:

[0119] The word segmentation processing module 610 is configured to obtain the historical voice data of the user and perform word segmentation processing on the text corresponding to the historical voice data;

[0120] A first target real scene determination module 620 is configured to match the word segmentation result with keywords in a first word library to determine a first target real scene corresponding to the historical voice data, wherein the first word library includes keywords for indicating different real scenes;

[0121] The preset keyword matching module 630 is configured to obtain a second word library corresponding to the first target real scene, and match the word segmentation result of the text corresponding to the historical voice data with the preset keywords in the second word library;

[0122] The information acquisition module 640 is configured to determine the target preset keyword that is successfully matched in the second vocabulary, and acquire the explanation recommendation information associated with the target preset keyword;

[0123] The information push module 650 is configured to push the explanation recommendation information to the client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information;

[0124] The historical voice data is determined based on the communication voice between the value-added developer and the user when they experience online virtual reality scenes corresponding to different real scenes associated with the marketing product.

[0125] In some exemplary implementations, based on the aforementioned embodiments, the explanation recommendation information includes one or more of the explanation words, promotional pictures, and promotional videos associated with the target preset keywords.

[0126] In some exemplary embodiments, based on the aforementioned embodiments, the word segmentation processing module 610 is further specifically configured to: obtain historical behavior data of the user, the historical behavior data being determined based on the interactive operations of the user when experiencing virtual reality scenes corresponding to different real scenes associated with marketing products online; based on the historical behavior data, counting the total number of interactive operations performed by the user to determine the user category of the user based on the total number of interactive operations; when the user category is a target user category, obtaining the user's historical voice data, and performing word segmentation processing on the text corresponding to the historical voice data.

[0127] In some exemplary embodiments, based on the aforementioned embodiments, the device 600 also includes a first offline explanation object determination module, which is configured to: input the text corresponding to the historical voice data into a sentiment analysis model to determine the target sentiment category corresponding to the historical voice data; when the target sentiment category represents that the user is interested in the first target real scene, push the identifier of the first target real scene to the client of the value-added developer, so that the value-added developer can determine the first target real scene as the first offline explanation object according to the identifier of the first target real scene.

[0128] In some exemplary embodiments, based on the aforementioned embodiments, the device 600 further includes a second offline explanation object determination module, which is configured to: obtain the user's historical behavior data, the historical behavior data being determined based on the user's interactive operations when experiencing virtual reality scenes corresponding to different real scenes online; based on the historical behavior data, determine the second target real scene that the user is interested in in different real scenes; push the identifier of the second target real scene to the client of the value-added developer, so that the value-added developer can determine the second target real scene as the second offline explanation object based on the identifier of the second target real scene. Wherein, the interactive operation includes one or more of click, drag, zoom, and slide when the user experiences virtual reality scenes corresponding to different real scenes associated with the marketing product online.

[0129] In some exemplary embodiments, based on the aforementioned embodiments, determining the second target real scene that the user is interested in in different real scenes based on the historical behavior data includes: determining the number of times the user interacts with each virtual reality scene respectively; sorting the number of interactive operations in descending order, and determining that the real scenes corresponding to the first N virtual reality scenes are the second target real scenes.

[0130] In some exemplary embodiments, based on the aforementioned embodiments, determining a second target real scene that the user is interested in in different real scenes based on the historical behavior data includes: determining the browsing time of the user for each virtual reality scene based on the historical behavior data; and determining the second target real scene based on the real scene corresponding to the virtual reality scene whose browsing time is greater than a preset value.

[0131] The specific details of each unit in the above-mentioned information pushing device have been described in detail in the corresponding information pushing method, so they will not be repeated here.

[0132] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0133] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0134] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0135] In the exemplary embodiments of the present disclosure, a computer storage medium capable of implementing the above method is also provided. A program product capable of implementing the above method of this specification is stored thereon. In some possible embodiments, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0136] refer to Figure 7 As shown, a program product 700 for implementing the above method according to an embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0137] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 above.

[0138] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0139] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0140] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0141] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0142] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0143] Refer to the following Figure 8 The electronic device 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0144] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include, but are not limited to: the at least one processing unit 810, the at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0145] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the following steps: Figure 1 The steps shown in Figure 2 , Figure 3 , Figure 4 , Figure 5The steps shown in .

[0146] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 8201 and / or a cache storage unit 8202 , and may further include a read-only storage unit (ROM) 8203 .

[0147] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0148] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0149] The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0150] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0151] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0152] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. An information push method, characterized in that: include: Acquire historical voice data of the user, and perform word segmentation processing on the text corresponding to the historical voice data; Matching the word segmentation result with keywords in a first vocabulary to determine a first target real scene corresponding to the historical voice data, wherein the first vocabulary includes keywords for representing different real scenes, wherein the different real scenes include different life scenes; Acquire a second word library associated with the first target real scene, and match the word segmentation result of the text corresponding to the historical voice data with preset keywords in the second word library; Determine a target preset keyword that matches successfully in the second vocabulary, and obtain explanation recommendation information associated with the target preset keyword; Pushing the explanation recommendation information to a client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information; The historical voice data is determined based on the communication voice when the value-added developer assists the user in experiencing online virtual reality scenes corresponding to different real scenes.

2. The information push method according to claim 1, characterized in that: The explanation recommendation information includes one or more of explanation words, promotional pictures, and promotional videos associated with the target preset keywords.

3. The information push method according to claim 1, characterized in that: The acquiring of historical voice data of the user and performing word segmentation processing on the text corresponding to the historical voice data includes: Acquiring historical behavior data of the user, where the historical behavior data is determined based on interactive operations of the user when experiencing virtual reality scenes corresponding to different real scenes online; Based on the historical behavior data, counting the total number of interactive operations performed by the user, so as to determine the user category of the user according to the total number of interactive operations; When the user category is the target user category, historical voice data of the user is acquired, and word segmentation processing is performed on the text corresponding to the historical voice data.

4. The information push method according to claim 1, characterized in that: After determining the first target real scene corresponding to the historical voice data, the method further includes: Inputting the text corresponding to the historical speech data into a sentiment analysis model to determine the target sentiment category corresponding to the historical speech data; When the target emotion category represents that the user is interested in the first target real scene, the identifier of the first target real scene is pushed to the client of the value-added developer, so that the value-added developer can determine the first target real scene as the first offline explanation object according to the identifier.

5. The information push method according to claim 1, characterized in that: The method further comprises: Acquiring historical behavior data of the user, where the historical behavior data is determined based on interactive operations of the user when experiencing virtual reality scenes corresponding to different real scenes online; Based on the historical behavior data, determining a second target real scene that the user is interested in among the different real scenes; Pushing the identifier of the second target real scene to the client of the value-added developer, so that the value-added developer can determine the second target real scene as the second offline explanation object according to the identifier; The interactive operation includes one or more of clicking, dragging, zooming, and sliding when the user experiences virtual reality scenes corresponding to different real scenes online.

6. The information push method according to claim 5, characterized in that: The determining, based on the historical behavior data, a second target real scene that the user is interested in among the different real scenes includes: Determining the number of times the user performs interactive operations on each virtual reality scene; The number of interaction operations is sorted in descending order, and the real scene corresponding to the first N virtual reality scenes is determined as the second target real scene.

7. The information push method according to claim 5, characterized in that: The determining, based on the historical behavior data, the second target real scene of interest in the different real scenes includes: Based on the historical behavior data, determining the browsing time of each virtual reality scene by the user; The second target real scene is determined according to the real scene corresponding to the virtual reality scene whose browsing time is longer than a preset value.

8. An information push device, characterized in that: include: A word segmentation processing module, which obtains the user's historical voice data and performs word segmentation processing on the text corresponding to the historical voice data; A first target real scene determination module is configured to match the word segmentation result with keywords in a first word library to determine a first target real scene corresponding to the historical voice data, wherein the first word library includes keywords for representing different real scenes, and the different real scenes include different life scenes; A preset keyword matching module is configured to obtain a second word library corresponding to the first target real scene, and match the word segmentation result of the text corresponding to the historical voice data with the preset keywords in the second word library; An information acquisition module is configured to determine a target preset keyword that is successfully matched in the second vocabulary, and acquire explanation recommendation information associated with the target preset keyword; An information push module is configured to push the explanation recommendation information to a client corresponding to the value-added developer, so that the value-added developer can explain the first target real scene to the user offline according to the explanation recommendation information; The historical voice data is determined based on the communication voice when the value-added developer assists the user in experiencing online virtual reality scenes corresponding to different real scenes.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the information pushing method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the information push method as described in any one of claims 1 to 7.

Images