Method, device, medium and program product for determining user profile information

Abstract

The purpose of this application is to provide a method, device, medium and program product for determining user portrait information, the method comprising obtaining multiple voice messages of a user in a target application; determining voice feature information corresponding to each of the multiple voice messages; based on the voice feature information corresponding to each of the multiple voice messages, determining one or more first portrait information corresponding to the user under the multiple voice messages; based on the one or more first portrait information and in combination with the collection relationship to which the first object belongs, determining the second portrait information of the user under the multiple voice messages, thereby constructing the user's portrait information based on the voice information of the user's daily communication with other users in the target application, without having to rely on the user's active interactive behavior in the target application.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a technology for determining user portrait information. Background Art

[0002] User portrait is a labeled user model abstracted from information such as user social attributes, living habits and consumption behavior. The core work of building user portrait is to label users, and labels are highly refined feature identifiers obtained through analysis of user information. Currently, general user portraits rely on users' active interactive behaviors, such as click events, browsing events, etc. The scope of information collection is relatively narrow and there are relatively few scenarios in which they can be used. Summary of the invention

[0003] One object of the present application is to provide a method, device, medium and program product for determining user portrait information.

[0004] According to one aspect of the present application, a method for determining user portrait information is provided, which is applied to a network device, and the method includes:

[0005] Get multiple voice messages of the user in the target application;

[0006] Determine voice feature information corresponding to each of the plurality of voice information, wherein the voice feature information includes one or more components corresponding to the voice information and assignment information corresponding to each component;

[0007] Based on the voice feature information corresponding to each of the multiple voice messages, determine one or more first portrait information corresponding to the user under the multiple voice messages, wherein the first portrait information includes a first object and assignment information corresponding to the first object, and the first object is selected from the one or more components;

[0008] Based on the one or more first portrait information and in combination with the set relationship to which the first object belongs, the second portrait information of the user under the multiple voice messages is determined, wherein the second portrait information includes one or more second objects and the assignment information corresponding to each second object. In the set relationship, the set corresponding to at least one of the second objects contains several of the first objects, and the assignment information corresponding to the at least one second object is determined based on the assignment information corresponding to the several first objects.

[0009] According to one aspect of the present application, a network device for determining user portrait information is provided, the device comprising:

[0010] A module for obtaining multiple voice messages of a user in a target application;

[0011] A module 12, used for determining voice feature information corresponding to each of the plurality of voice information, wherein the voice feature information includes one or more components corresponding to the voice information and assignment information corresponding to each component;

[0012] A module 3 is used to determine one or more first portrait information corresponding to the user under the multiple voice messages based on the voice feature information corresponding to each voice message in the multiple voice messages, wherein the first portrait information includes a first object and assignment information corresponding to the first object, and the first object is selected from the one or more components;

[0013] A four-module is used to determine the second portrait information of the user under the multiple voice messages based on the one or more first portrait information and in combination with the set relationship to which the first object belongs, wherein the second portrait information includes one or more second objects and the assignment information corresponding to each second object. In the set relationship, the set corresponding to at least one of the second objects contains several of the first objects, and the assignment information corresponding to the at least one second object is determined based on the assignment information corresponding to the several first objects.

[0014] According to one aspect of the present application, a computer device for determining user portrait information is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the operation of any of the methods described above.

[0015] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the operation of any of the methods described above is implemented.

[0016] According to one aspect of the present application, a computer program product is provided, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0017] Compared with the prior art, the network device in the present application extracts and assigns features to each voice message sent by the user, determines the corresponding voice feature information, generates the first portrait information of the user based on the voice feature information corresponding to each voice message, and then determines the second portrait information of the user based on the set relationship to which each first portrait information belongs. The present application can form or deepen the user portrait information of the target user based on the intonation, tone and voice content in the voice message sent by the target user, thereby making the construction of the user portrait information more accurate and comprehensive. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0019] Figure 1 A flow chart of a method for determining user portrait information according to an embodiment of the present application is shown;

[0020] Figure 2 A flow chart of a method for determining user portrait information according to another embodiment of the present application is shown;

[0021] Figure 3 A flowchart showing a method for determining user portrait information according to another embodiment of the present application is shown.

[0022] Figure 4 A network device structure diagram for determining user portrait information according to an embodiment of the present application is shown;

[0023] Figure 5 An exemplary system is shown that can be used to implement the various embodiments described in this application.

[0024] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0025] The present application is described in further detail below in conjunction with the accompanying drawings.

[0026] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (eg, a central processing unit (CPU)), an input / output interface, a network interface and a memory.

[0027] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory. Memory is an example of a computer-readable medium.

[0028] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, Phase-Change Memory (PCM), Programmable Random Access Memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of random access memory (RAM), Read-Only Memory (ROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0029] The devices referred to in this application include but are not limited to terminals, network devices, or devices formed by integrating terminals and network devices through a network. The terminal includes but is not limited to any mobile electronic product that can interact with a user (for example, interact with a user through a touchpad), such as a smart phone, a tablet computer, etc. The mobile electronic product can use any operating system, such as an Android operating system, an iOS operating system, etc. Among them, the network device includes an electronic device that can automatically perform numerical calculations and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc. The network device includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud composed of multiple servers; here, the cloud is composed of a large number of computers or network servers based on cloud computing (Cloud Computing), wherein cloud computing is a type of distributed computing, a virtual supercomputer composed of a group of loosely coupled computer sets. The network includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, VPN network, wireless self-organizing network (Ad Hoc network), etc. Preferably, the device may also be a program running on the terminal, network device, or a device formed by integrating the terminal and network device, network device, touch terminal, or network device and touch terminal through a network.

[0030] Of course, those skilled in the art should understand that the above-mentioned devices are only examples, and other existing or future devices that are applicable to the present application should also be included in the scope of protection of the present application and are included here by reference.

[0031] In the description of the present application, “plurality” means two or more, unless otherwise clearly and specifically defined.

[0032] Figure 1A flow chart of a method for determining user portrait information according to an embodiment of the present application is shown, the method comprising step S11, step S12, step S13, and step S14. Step S11, the network device obtains multiple voice messages of the user in the target application; Step S12, the network device determines the voice feature information corresponding to each of the multiple voice messages, wherein the voice feature information includes one or more components corresponding to the voice message and the assignment information corresponding to each component; Step S13, the network device determines one or more first portrait information corresponding to the user under the multiple voice messages based on the voice feature information corresponding to each of the multiple voice messages, wherein the first portrait information includes a first object and the assignment information corresponding to the first object, and the first object is selected from the one or more components; Step S14, the network device determines the second portrait information of the user under the multiple voice messages based on the one or more first portrait information and in combination with the set relationship to which the first object belongs, wherein the second portrait information includes one or more second objects and the assignment information corresponding to each second object, and in the set relationship, the set corresponding to at least one of the second objects contains several of the first objects, and the assignment information corresponding to the at least one second object is determined based on the assignment information corresponding to the several first objects.

[0033] In step S11, the network device obtains multiple voice messages of the user in the target application. In some embodiments, the target application includes an application with a social function, and the target application has a voice input function, and the user can publish voice messages in the target application to communicate with other users. In some embodiments, the network device can obtain multiple voice messages of the user in the target application within a preset time period. For example, the network device obtains the voice information of the user in the target application within one day, or the difference between the release time point of the voice obtained by the network device and the current time point is less than or equal to the preset time difference threshold. In some embodiments, the network device first obtains multiple candidate voice messages of the user in the target application, and then determines the corresponding multiple voice messages from the candidate voice messages. For example, voice messages with a voice duration greater than a preset voice duration are screened from the candidate voice messages. For another example, the network device converts each candidate voice message into a voice text message, and performs word segmentation processing on each voice text message, and determines multiple voice messages from it according to the word segmentation result of each candidate voice message. For example, the network device detects whether the voice text message corresponding to the candidate voice message includes the three basic parts of speech of subject, verb, and noun. If included, the candidate voice message is determined as voice information. In some embodiments, the network device obtains one or more candidate voice messages of the user in the target application, and determines multiple voice messages based on the one or more candidate voice messages, wherein the text information corresponding to each voice message includes only one sentence. For example, the network device first segments the candidate voice messages so that the determined voice messages only include one sentence.

[0034] In step S12, the network device determines the voice feature information corresponding to each of the multiple voice messages, wherein the voice feature information includes one or more components corresponding to the voice message and the value assignment information corresponding to each component. For example, the network device converts each voice message into text information, and determines one or more keywords corresponding to the voice message and the value assignment information corresponding to the keywords based on the text information. For another example, the network device can perform a corresponding intonation or tone analysis on each voice message, and determine the tone assignment corresponding to the voice message according to a preset tone scoring standard.

[0035] In some embodiments, the components include at least one of the following: one or more keyword information corresponding to the voice information; tone information corresponding to the voice information; person information corresponding to the voice information. For example, the tone information and person information in each voice information are carried by the voice information itself, and the keyword information in the voice information is extracted from the text information corresponding to the voice information.

[0036] In some embodiments, the component includes tone information corresponding to the voice information. The network device first performs intonation or tone analysis on the voice information to determine the tone type corresponding to the voice information, and then determines the assignment information corresponding to the tone information in the voice information based on the tone type and the corresponding mapping relationship between the tone type and the assignment (for example, refer to the tone type assignment table shown in Table 1).

[0037] Table 1 Tone type assignment table

[0038] Tone Type Questions / rhetorical questions plain sentence Exclamatory Sentences Assignment 0 0.5 1

[0039] In some embodiments, the component includes person information corresponding to the voice information. The network device first determines the text information corresponding to the voice information, and then determines the person type corresponding to the voice information from the text information, and determines the assignment information corresponding to the person information in the voice information based on the person type and the corresponding mapping relationship between the person type and the assignment (for example, refer to the person type assignment table shown in Table 2).

[0040] Table 2 Person type assignment table

[0041] Type of person First Person Second / Third Person Assignment 1 0

[0042] In some embodiments, the component includes one or more keyword information corresponding to the voice information; the step S12 includes: step S121 (not shown), the network device determines the text information corresponding to each of the multiple voice information; step S122 (not shown), the network device determines the one or more keyword information corresponding to the voice information and the assignment information corresponding to each keyword information based on the text information corresponding to each voice information. For example, the network device converts the voice information into text information, and determines the one or more keyword information corresponding to the voice information by performing word segmentation and part-of-speech analysis on the text information. Among them, the keyword information is a noun. The network device determines the assignment information corresponding to the keyword information based on the keyword information.

[0043] In some embodiments, the step S122 includes: the network device extracts one or more keyword information and judgment word information corresponding to each keyword information from the text information; based on the classification information to which the judgment word information belongs, determines the assignment information corresponding to each keyword information.

[0044] In some embodiments, the network device converts the voice information into text information, and extracts one or more verbs and nouns from the text information by performing word segmentation and part-of-speech analysis on the text information. The network device may determine one or more keyword information corresponding to the voice information based on the one or more nouns, and determine the judgment word information corresponding to the keyword information according to the text distance between the keyword information and the verb in the text information, wherein the text distance is the number of characters between the keyword information and the verb in the text information. The text distance between the keyword information and the judgment word information corresponding to it is less than or equal to the preset text distance threshold, or the text distance between the keyword information and the judgment word information corresponding to it is less than the text distance between the keyword information and other verbs in the text information. Taking a voice message as an example, the voice message is converted into text information as "I like playing basketball and hate watching movies". The network device can extract the nouns "basketball" and "movie" as the keyword information corresponding to the voice message, and use the verb "like" which is close to the text distance of "basketball" as the judgment word information corresponding to the keyword information "basketball", and use the verb "hate" which is close to the text distance of "movie" as the judgment word information corresponding to the keyword information "movie".

[0045] In some embodiments, the network device may construct a corresponding word library based on whether the verb has obvious emotional color and the type of emotional color it has. For example, the general word library corresponds to verbs without obvious emotional color (for example, come back, wipe, etc.), the progressive word library corresponds to verbs with positive emotional color (for example, like, want, etc.), and the regressive word library corresponds to verbs with negative emotional color (for example, hate, hate, etc.). The network device may determine the corresponding classification information according to the word library to which the judgment word information belongs, and the classification information includes general vocabulary, progressive vocabulary or regressive vocabulary. The network device may determine the assignment information corresponding to the keyword information based on the classification information and the mapping relationship between the corresponding classification information and the assignment (for example, refer to the classification information assignment table shown in Table 3).

[0046] Table 3 Classification information assignment table

[0047] Classified Information General Vocabulary Progressive vocabulary Retrograde vocabulary Assignment 0.5 1 -0.5

[0048] For example, for the aforementioned voice information "I like playing basketball, but hate watching movies", the judgment word information corresponding to the keyword information "basketball" is "like", which belongs to the progressive vocabulary, so the corresponding value of the keyword information "basketball" is 1; the judgment word information corresponding to the keyword information "movie" is "hate", which belongs to the regressive vocabulary, so the corresponding value of the keyword information "movie" is -0.5. Then, the voice feature information corresponding to the voice information can be determined as shown in Table 4 below.

[0049] Table 4 Voice feature information table

[0050]

[0051] In step S13, the network device determines one or more first portrait information corresponding to the user under the multiple voice messages based on the voice feature information corresponding to each voice message in the multiple voice messages, wherein the first portrait information includes a first object and the assignment information corresponding to the first object, and the first object is selected from the one or more components. For example, the network device merges the voice feature information containing the same keyword information to determine one or more first portrait information. For example, the network device can merge the voice feature information containing the keyword information "basketball" to determine the corresponding first portrait information, the first object included in the first portrait information is "basketball", and the assignment information corresponding to the first object is NW = ∑Vi*Pi*Wi / n, wherein Vi is the tone information assignment corresponding to the i-th voice feature information containing the keyword information "basketball", Pi is the person information assignment corresponding to the i-th voice feature information containing the keyword information "basketball", Wi is the "basketball" keyword information assignment corresponding to the i-th voice feature information containing the keyword information "basketball", and n is the total number of voice feature information containing the keyword information "basketball".

[0052] In some embodiments, the step S13 includes: step S131 (not shown), the network device determines one or more first voice feature information from the voice feature information corresponding to each voice information in the multiple voice information, wherein the target component in the first voice feature information matches the component in other first voice feature information; step S132 (not shown), the network device determines the first portrait information corresponding to the user under the multiple voice information based on the one or more first voice feature information, wherein the first portrait information includes a first object and the assignment information corresponding to the first object, and the first object matches the target component. For example, the network device can determine one or more first voice feature information from the voice feature information corresponding to each voice information in the multiple voice information based on the keyword information contained in the voice feature information, the determined first voice feature information all contain the same target keyword information, and the first object matches the target keyword information. The network device then determines the assignment information corresponding to the first object according to the assignment information corresponding to the corresponding component contained in each first voice feature information (for example, the assignment information of the target keyword information, the assignment information of the person information, or the assignment information of the tone information).

[0053] In some embodiments, the step S132 includes: step S1321 (not shown), the network device determines the current assignment information of the first object matching the target component according to the assignment information corresponding to the target component in the one or more first voice feature information, so as to obtain the current first portrait information corresponding to the user under the multiple voice information; step S1322 (not shown), the network device determines the first portrait information according to the current first portrait information and the historical first portrait information corresponding to the first object, wherein the first portrait information includes a first object and the assignment information corresponding to the first object. In some embodiments, the assignment information corresponding to the target component includes the keyword information assignment information corresponding to the target component, the person information assignment information in the first voice feature information, or the tone information assignment information. The network device can determine the current assignment information corresponding to the first object in the current first portrait information according to the assignment information corresponding to the target component, and then determine the current first portrait information. In some embodiments, the network device also stores the historical portrait information of the user. If there is historical first portrait information matching the first object in the historical portrait information of the user, the first portrait information of the user can be determined based on the historical first portrait information and the current first portrait information, so that the first portrait information of the user can be continuously updated based on the user's current chat voice to ensure the timeliness of the first portrait information. For example, the network device can determine the assignment information corresponding to the first object in the historical first portrait information (for example, calculate the average value of the two, etc.) based on the historical assignment information corresponding to the first object in the historical first portrait information and the current assignment information corresponding to the first object in the current first portrait information, and then determine the first portrait information based on the assignment information corresponding to the first object.

[0054] In some embodiments, the step S1322 includes: step S13221 (not shown), the network device determines the corresponding first portrait difference information according to the current first portrait information and the historical first portrait information corresponding to the first object; step S13222 (not shown), the network device determines the first portrait information based on the first portrait difference information. In some embodiments, the network device only needs to determine new first portrait information when there is a large difference between the historical value assignment information corresponding to the historical first portrait information and the current value assignment information corresponding to the current first portrait information, and update the historical first portrait information based on the first portrait information; if the difference between the historical value assignment information and the current value assignment information is small, the historical first portrait information can be directly used as the first portrait information.

[0055] In some embodiments, the step S13222 includes: detecting whether the first portrait difference information is within a preset difference interval, and if the first portrait difference information is within the preset difference interval, using the historical first portrait information as the first portrait information; otherwise, determining the first portrait information based on the current first portrait information and the historical first portrait information, and updating the historical first portrait information based on the first portrait information. In some embodiments, if the first portrait difference information is not within the preset difference interval, it can be considered that the user's preference for a certain thing has changed, and the network device needs to update the user's first portrait information. In addition, in order to prevent feature reversal, the network device can set a corresponding step size to update the preference degree information. The step length can be determined based on the current first portrait information: step length = NW / (n+1), where NW is the current assignment information, n is the number of first voice feature information, and the step length has a value range of [-0.1, 0.1], that is, if the value calculated according to NW / (n+1) is less than -0.1, then the step length is -0.1; if the value calculated according to NW / (n+1) is greater than 0.1, then the step length is 0.1. Based on the step length and the historical first portrait information, the network device can determine the first portrait information and update the historical first portrait information.

[0056] In step S14, the network device determines the second portrait information of the user under the multiple voice messages based on the one or more first portrait information and in combination with the set relationship to which the first object belongs, wherein the second portrait information includes one or more second objects and the assignment information corresponding to each second object, and in the set relationship, the set corresponding to at least one of the second objects contains several first objects, and the assignment information corresponding to the at least one second object is determined based on the assignment information corresponding to the several first objects. In some embodiments, since the first object is often a specific thing, the first portrait information obtained in this way is often very scattered, which is not conducive to analyzing user preferences. Based on the one or more first portrait information obtained, the network device can aggregate the first portrait information of the first object belonging to the same set based on the set relationship to which the first object belongs, and determine the second portrait information of the user under the multiple voice messages. In some embodiments, the set relationship includes large category features such as sports, electronic games, and art exhibitions. For example, the network device determines multiple first portrait information, wherein the first objects included in each first portrait information are "basketball", "swimming", "football", "Final Fantasy", and "World of Warcraft" respectively. The network device can determine that first objects such as "basketball", "swimming", and "football" belong to the sports set, and first objects such as "Final Fantasy" and "World of Warcraft" belong to the video game set. The network device can determine the corresponding second objects "sports" and "video games" based on the set relationship to which these first objects belong, and determine the assignment information corresponding to the corresponding second objects based on the assignment information corresponding to the first objects belonging to the same set, and then determine the second portrait information based on the second objects "sports" and "video games" and their corresponding assignment information. In this way, the user's preferences for specific things are aggregated, and the user's preferences for various categories of things are determined, which is conducive to the in-depth characterization of user portrait information.

[0057] In some embodiments, the step S14 includes: step S141 (not shown), the network device determines one or more portrait information sets based on the one or more first portrait information and in combination with the set relationship to which the first object belongs, wherein the portrait information set includes a plurality of first portrait information, and the first objects corresponding to the first portrait information in the portrait information set belong to the same set in the set relationship; step S142 (not shown), the network device determines the second portrait information of the user under the multiple voice messages based on the one or more portrait information sets. For example, the network device first divides the first portrait information corresponding to the first objects belonging to the same set into the same portrait information set based on the set relationship to which the first objects belong. The network device then determines the second object corresponding to each portrait information set and the corresponding second object assignment information based on the determined one or more portrait information sets, and then determines the second portrait information.

[0058] In some embodiments, the step S142 includes: step S1421 (not shown), the network device determines the second object corresponding to the portrait information set and the assignment information corresponding to the second object for each portrait information set in the one or more portrait information sets according to each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship contains the first object of each first portrait information in the portrait information set; step S1422 (not shown), the network device generates the second portrait information of the user under the multiple voice messages according to the second object corresponding to each portrait information set in the one or more portrait information sets and the assignment information corresponding to the second object. In some embodiments, after determining the portrait information set, the network device can determine the second object corresponding to the portrait information set according to the set relationship to which the first object included in each first portrait information in each portrait information set belongs. For example, if each first object in the portrait information set belongs to a sports set, it can be determined that the second object corresponding to the portrait information set is "sports". The network device can also determine the assignment information corresponding to the second object according to the assignment information of the first object corresponding to each first portrait information in the portrait information set. After determining the second object corresponding to each portrait information set and the assignment information corresponding to the second object, the network device can determine the second portrait information based on each second object and the assignment information corresponding to the second object, wherein the second portrait information includes one or more second objects and the assignment information corresponding to each second object.

[0059] In some embodiments, the step S1421 includes: step S14211 (not shown), the network device determines the second object corresponding to the portrait information set according to the first object corresponding to each first portrait information in the portrait information set for each portrait information set in the one or more portrait information sets, wherein the set corresponding to the second object in the set relationship includes the first object of each first portrait information in the portrait information set; step S14212 (not shown), the network device determines the assignment information corresponding to the second object according to the assignment information of the first object corresponding to each first portrait information in the portrait information set. For example, the network device may determine the second object corresponding to the portrait information set according to the set relationship to which the first object included in each first portrait information in each portrait information set belongs. In some embodiments, the network device may calculate the assignment information corresponding to the second object according to the assignment information of the first object corresponding to each first portrait information in the portrait information set, for example, the network device may use the average value of the assignment information of each first object as the assignment information corresponding to the second object.

[0060] In some embodiments, the step S14212 includes: the network device determines the assignment information corresponding to the second object based on the assignment information of the first object of each first portrait information in the portrait information set and the following formula: N = ∑NWi*Ni*Ei / ∑Ni, where N is the assignment information corresponding to the second object, NWi is the assignment information of the first object corresponding to the i-th first portrait information in the portrait information set, Ni is the number of voice feature information corresponding to the i-th first portrait information, and Ei is the credibility information corresponding to the i-th first portrait information. In some embodiments, the credibility information Ei is positively correlated with the number Ni of voice feature information corresponding to the first portrait information, and the higher the number of voice feature information corresponding to the first portrait information, the higher the credibility corresponding to the first portrait information.

[0061] In some embodiments, the step S14211 includes: for each portrait information set in the one or more portrait information sets, if the total number of first portrait information in the portrait information set exceeds a predetermined quantity threshold, the network device determines the second object corresponding to the portrait information set according to the first object of each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship includes the first object of each first portrait information in the portrait information set; otherwise, directly record the first object of each first portrait information in the portrait information set as the second object corresponding to the portrait information set. For example, if the total number of first portrait information in the portrait information set exceeds a predetermined quantity threshold, it is considered that the first portrait information needs to be aggregated in order to accurately determine the user preference from the complex data. The network device can determine the second object corresponding to the portrait information set according to the set relationship to which the first object included in each first portrait information in the portrait information set belongs, and determine the assignment information N=∑NWi*Ni*Ei / ∑Ni corresponding to the second object. If the number of the first portrait information in the portrait information set is less than or equal to the quantity threshold, for example, the number of the first portrait information in the portrait information set is only countable, then the first object in each first portrait information can be directly determined as the second object corresponding to the portrait information set, so that when the number of first portrait information in the portrait information set is small, user features can be retained as much as possible to avoid some user features being masked due to direct aggregation.

[0062] In some embodiments, the method further includes: step S15 (not shown), the network device updates the historical second portrait information according to the second portrait information and the historical second portrait information corresponding to the user. In some embodiments, the network device may determine the corresponding second portrait information based on the newly acquired voice information of the user in the target application, and update the historical second portrait information according to the second portrait information, thereby ensuring that the historical second user portrait information of the user stored by the network device matches the current behavior habits or characteristics of the user.

[0063] Figure 2 A flow chart of a method for determining user portrait information according to an embodiment of the present application is shown. The user device provides a voice channel to the user (for example, a voice call in a voice chat room or a social application, etc.), the user speaks in the voice channel, the network device obtains the voice information of the user's speech, and uses a sentiment analyzer to perform intonation and tone analysis, and uses a text analyzer to perform word segmentation and keyword extraction. The network device can determine the user's characteristics (for example, the user's preference for a certain thing or a certain type of thing) based on the intonation and tone analysis results and the corresponding keyword information, and then update the user portrait based on the characteristics. Thus, a user portrait of the user is constructed from the user's daily communication with others.

[0064] Figure 3 A flowchart of a method for determining user portrait information according to an embodiment of the present application is shown. For each voice message of the user, the network device obtains the single sentence feature of the voice message, and determines the feature weight through the auxiliary sense word library (for example, determines the corresponding assignment of keyword information through the word library to which the judgment word information belongs), and then combines with the historical feature library to form a single classification feature corresponding to the user. The network device then classifies each feature through the clustering word library to obtain a clustering feature. In some embodiments, the network device determines the clustering feature in combination with the historical clustering library, and uses the clustering feature to update the user portrait.

[0065] Figure 4A structural diagram of a network device for determining user portrait information according to an embodiment of the present application is shown, wherein the network device includes a one-module 11, a one-two module 12, a one-three module 13 and a one-four module 14. The one-to-one module 11 obtains multiple voice messages of the user in the target application; the one-to-two module 12 determines the voice feature information corresponding to each of the multiple voice messages, wherein the voice feature information includes one or more components corresponding to the voice message and the assignment information corresponding to each component; the one-to-three module 13 determines one or more first portrait information corresponding to the user under the multiple voice messages based on the voice feature information corresponding to each of the multiple voice messages, wherein the first portrait information includes a first object and the assignment information corresponding to the first object, and the first object is selected from the one or more components; the one-to-four module 104 determines the second portrait information of the user under the multiple voice messages based on the one or more first portrait information and in combination with the set relationship to which the first object belongs, wherein the second portrait information includes one or more second objects and the assignment information corresponding to each second object, and in the set relationship, at least one set corresponding to the second object contains several first objects, and the assignment information corresponding to the at least one second object is determined based on the assignment information corresponding to the several first objects. Here, the Figure 4 The specific implementations corresponding to the one-to-one module 11, the one-to-two module 12, the one-to-three module 13 and the one-to-four module 14 shown are respectively the same as or similar to the specific implementations of the aforementioned steps S11, S12, S13 and S14, so they are not repeated here and are included herein by reference.

[0066] In some embodiments, the one-two module 12 includes a one-two-one unit 121 (not shown) and a one-two-two unit 122 (not shown). The one-two-one unit 121 determines the text information corresponding to each of the multiple voice messages; the one-two-two unit 122 determines one or more keyword information corresponding to the voice message and the assignment information corresponding to each keyword information based on the text information corresponding to each voice message. Here, the specific implementation methods of the one-two-one unit 121 and the one-two-two unit 122 are respectively the same or similar to the specific implementation methods of the aforementioned step S121 and step S122, so they are not repeated here and are included here by reference.

[0067] In some embodiments, the one-three module 13 includes a one-three-one unit 131 (not shown) and a one-three-two unit 132 (not shown). The one-three-one unit 131 determines one or more first voice feature information from the voice feature information corresponding to each voice information in the multiple voice information, wherein the target component in the first voice feature information matches the component in other first voice feature information, and the one-three-two unit 132 determines the first portrait information corresponding to the user under the multiple voice information based on the one or more first voice feature information, wherein the first portrait information includes a first object and the assignment information corresponding to the first object, and the first object matches the target component. Here, the specific implementation methods of the one-three-one unit 131 and the one-three-two unit 132 are respectively the same or similar to the specific implementation methods of the aforementioned steps S131 and S132, so they are not repeated here and are included here by reference.

[0068] In some embodiments, the 132 unit 132 includes: a 1321 subunit 1321 (not shown) and a 1322 subunit 1322 (not shown). The 1321 subunit 1321 determines the current assignment information of the first object matching the target component according to the assignment information corresponding to the target component in the one or more first voice feature information, so as to obtain the current first portrait information corresponding to the user under the multiple voice information; the 1322 subunit 1322 determines the first portrait information according to the current first portrait information and the historical first portrait information corresponding to the first object, wherein the first portrait information includes a first object and the assignment information corresponding to the first object. Here, the specific implementation methods of the 1321 subunit 1321 and the 1322 subunit 1322 are respectively the same or similar to the specific implementation methods of the aforementioned steps S1321 and S1322, so they are not repeated here and are included here by reference.

[0069] In some embodiments, the 1322 subunit 1322 includes a 13221 molecular unit 13221 (not shown) and a 13222 molecular unit 13222 (not shown). The 13221 molecular unit 13221 determines the corresponding first portrait difference information according to the current first portrait information and the historical first portrait information corresponding to the first object; the 13222 molecular unit 13222 determines the first portrait information based on the first portrait difference information. Here, the specific implementations of the 13221 molecular unit 13221 and the 13222 molecular unit 13222 are respectively the same or similar to the specific embodiments of the aforementioned step S13221 and step S13222, so they are not repeated here and are included here by reference.

[0070] In some embodiments, the one-fourth module 14 includes a one-fourth-one unit 141 (not shown) and a one-fourth-two unit 142 (not shown). The one-fourth-one unit 141 determines one or more portrait information sets based on the one or more first portrait information and in combination with the set relationship to which the first object belongs, wherein the portrait information set includes a plurality of first portrait information, and the first objects corresponding to the first portrait information in the portrait information set belong to the same set in the set relationship; the one-fourth-two unit 142 determines the second portrait information of the user under the multiple voice messages based on the one or more portrait information sets. Here, the specific implementation methods of the one-fourth-one unit 141 and the one-fourth-two unit 142 are respectively the same or similar to the specific implementation methods of the aforementioned steps S141 and S142, and therefore will not be repeated here and are included herein by reference.

[0071] In some embodiments, the 142 unit 142 includes a 1421 sub-unit 1421 (not shown) and a 1422 sub-unit 1422 (not shown). The 1421 sub-unit 1421 determines, for each portrait information set in the one or more portrait information sets, the second object corresponding to the portrait information set and the assignment information corresponding to the second object according to each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship contains the first object of each first portrait information in the portrait information set; the 1422 sub-unit 1422 generates the second portrait information of the user under the multiple voice messages according to the second object corresponding to each portrait information set in the one or more portrait information sets and the assignment information corresponding to the second object. Here, the specific implementation methods of the 1421 sub-unit 1421 and the 1422 sub-unit 1422 are respectively the same or similar to the specific implementation methods of the aforementioned steps S1421 and S1422, so they are not repeated here and are included here by reference.

[0072] In some embodiments, the 1421 subunit 1421 includes a 14211 molecular unit 14211 (not shown) and a 14212 molecular unit 14212 (not shown). The 14211 molecular unit 14211 determines, for each portrait information set in the one or more portrait information sets, the second object corresponding to the portrait information set according to the first object corresponding to each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship contains the first object of each first portrait information in the portrait information set; the 14212 molecular unit 14212 determines the assignment information corresponding to the second object according to the assignment information of the first object corresponding to each first portrait information in the portrait information set. Here, the specific implementation methods of the 14211 molecular unit 14211 and the 14212 molecular unit 14212 are respectively the same or similar to the specific embodiments of the aforementioned steps S14211 and S14212, so they are not repeated here and are included here by reference.

[0073] In some embodiments, the network device further includes a one-five module 15 (not shown), and the one-five module 15 updates the historical second portrait information according to the second portrait information and the historical second portrait information corresponding to the user. Here, the specific implementation of the one-five module 15 is the same or similar to the specific implementation of the aforementioned step S15, so it is not repeated here and is included here by reference.

[0074] In addition to the methods and devices described in the above embodiments, the present application also provides a computer-readable storage medium, which stores computer code. When the computer code is executed, the method described in any of the preceding items is executed.

[0075] The present application also provides a computer program product. When the computer program product is executed by a computer device, the method described in any of the preceding items is executed.

[0076] The present application also provides a computer device, the computer device comprising:

[0077] one or more processors;

[0078] a memory for storing one or more computer programs;

[0079] When the one or more computer programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any of the preceding items.

[0080] Figure 5 An exemplary system that can be used to implement various embodiments described in this application is shown;

[0081] like Figure 5 In some embodiments shown, the system 300 can be used as any of the devices in the various described embodiments. In some embodiments, the system 300 may include one or more computer-readable media (e.g., system memory or NVM / storage device 320) with instructions and one or more processors (e.g., (one or more) processors 305) coupled to the one or more computer-readable media and configured to execute instructions to implement modules to perform the actions described in this application.

[0082] For one embodiment, system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of processor(s) 305 and / or any suitable device or component in communication with system control module 310 .

[0083] The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. The memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0084] The system memory 315 may be used, for example, to load and store data and / or instructions for the system 300. For one embodiment, the system memory 315 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the system memory 315 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0085] For one embodiment, system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to NVM / storage device 320 and communication interface(s) 325 .

[0086] For example, NVM / storage device 320 may be used to store data and / or instructions. NVM / storage device 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0087] NVM / storage device 320 may include storage resources that are physically part of the device on which system 300 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 320 may be accessed over a network via communication interface(s) 325.

[0088] Communication interface(s) 325 may provide an interface for system 300 to communicate over one or more networks and / or with any other suitable devices. System 300 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0089] For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 (e.g., the memory controller module 330). For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310 to form a system on chip (SoC).

[0090] In various embodiments, the system 300 may be, but is not limited to: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the system 300 may have more or fewer components and / or a different architecture. For example, in some embodiments, the system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and a speaker.

[0091] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0092] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes but is not limited to source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0093] Communication media include media by which communication signals containing, for example, computer readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media may include guided transmission media such as cables and wires (e.g., fiber optic, coaxial, etc.) and wireless (unguided transmission) media that can propagate energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied as a modulated data signal in, for example, a wireless medium such as a carrier wave or similar mechanism such as embodied as part of spread spectrum technology. The term "modulated data signal" refers to a signal whose one or more characteristics are changed or set in such a manner as to encode information in the signal. Modulation may be analog, digital, or a hybrid modulation technique.

[0094] By way of example and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and non-volatile memory, such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or later developed that can store computer-readable information / data for use by a computer system.

[0095] Here, according to an embodiment of the present application, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run the methods and / or technical solutions based on the aforementioned multiple embodiments of the present application.

[0096] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for determining user portrait information, wherein: The method comprises: Get multiple voice messages of the user in the target application; Determine voice feature information corresponding to each of the plurality of voice information, wherein the voice feature information includes one or more components corresponding to the voice information and assignment information corresponding to each component; Based on the voice feature information corresponding to each of the multiple voice messages, determine one or more first portrait information corresponding to the user under the multiple voice messages, wherein the first portrait information includes a first object and assignment information corresponding to the first object, and the first object is selected from the one or more components; According to the one or more first portrait information and in combination with the set relationship to which the first object belongs, one or more portrait information sets are determined, wherein the portrait information set includes several first portrait information, and the first objects corresponding to the first portrait information in the portrait information set belong to the same set in the set relationship; according to the one or more portrait information sets, second portrait information of the user under the multiple voice messages is determined, wherein the second portrait information includes one or more second objects and the assignment information corresponding to each second object, and in the set relationship, the set corresponding to at least one of the second objects contains several first objects, and the assignment information corresponding to the at least one second object is determined based on the assignment information corresponding to the several first objects, wherein the set relationship is used to characterize the relationship that the first object belongs to a large category feature set; The components include at least one of the following: one or more keyword information corresponding to the voice information; tone information corresponding to the voice information; and person information corresponding to the voice information.

2. The method according to claim 1, wherein: The component includes one or more keyword information corresponding to the voice information; The determining of the voice feature information corresponding to each of the plurality of voice information, wherein the voice feature information includes one or more components corresponding to the voice information and the assignment information corresponding to each component includes: Determine the text information corresponding to each of the plurality of voice messages; According to the text information corresponding to each piece of voice information, one or more keyword information corresponding to the voice information and the value assignment information corresponding to each keyword information are determined.

3. The method according to claim 2, wherein: The step of determining, according to the text information corresponding to each piece of voice information, one or more keyword information corresponding to the voice information and the value assignment information corresponding to each keyword information comprises: Extracting one or more keyword information and judgment word information corresponding to each keyword information from the text information; Based on the classification information to which the judgment word information belongs, the assignment information corresponding to each keyword information is determined.

4. The method according to any one of claims 1 to 3, wherein: The method further comprises determining one or more first portrait information corresponding to the user under the plurality of voice messages based on the voice feature information corresponding to each voice message in the plurality of voice messages, wherein the first portrait information comprises a first object and assignment information corresponding to the first object, and the first object is selected from the one or more components including: Determine one or more first voice feature information from the voice feature information corresponding to each voice information in the plurality of voice information, wherein the target component in the first voice feature information matches the component in other first voice feature information; Based on the one or more first voice feature information, first portrait information corresponding to the user under the multiple voice information is determined, wherein the first portrait information includes a first object and assignment information corresponding to the first object, and the first object matches the target component.

5. The method according to claim 4, wherein: The determining, based on the one or more first voice feature information, first portrait information corresponding to the user under the multiple voice information, wherein the first portrait information includes a first object and assignment information corresponding to the first object, and the first object matches the target component including: Determine, according to the assignment information corresponding to the target component in the one or more first voice feature information, the current assignment information of the first object matching the target component, so as to obtain the current first portrait information corresponding to the user under the multiple voice information; The first portrait information is determined according to the current first portrait information and the historical first portrait information corresponding to the first object, wherein the first portrait information includes a first object and assignment information corresponding to the first object.

6. The method according to claim 5, wherein: The first portrait information is determined according to the current first portrait information and the historical first portrait information corresponding to the first object, wherein the first portrait information includes a first object and the assignment information corresponding to the first object includes: Determine corresponding first portrait difference information according to the current first portrait information and the historical first portrait information corresponding to the first object; Based on the first portrait difference information, determine the first portrait information.

7. The method according to claim 6, wherein: The determining the first portrait information based on the first portrait difference information includes: Detect whether the first portrait difference information is within a preset difference interval. If the first portrait difference information is within the preset difference interval, use the historical first portrait information as the first portrait information; otherwise, The first portrait information is determined according to the current first portrait information and the historical first portrait information, and the historical first portrait information is updated based on the first portrait information.

8. The method according to claim 1, wherein: The determining, according to the one or more portrait information sets, the second portrait information of the user under the multiple voice information includes: For each portrait information set in the one or more portrait information sets, determine the second object corresponding to the portrait information set and the assignment information corresponding to the second object according to each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship includes the first object of each first portrait information in the portrait information set; According to the second object corresponding to each portrait information set in the one or more portrait information sets and the assignment information corresponding to the second object, the second portrait information of the user under the multiple voice information is generated.

9. The method according to claim 8, wherein: For each portrait information set in the one or more portrait information sets, determining the second object corresponding to the portrait information set and the assignment information corresponding to the second object according to each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship contains the first object of each first portrait information in the portrait information set, including: For each portrait information set in the one or more portrait information sets, determining a second object corresponding to the portrait information set according to a first object corresponding to each first portrait information in the portrait information set, wherein in the set relationship, the set corresponding to the second object includes the first object of each first portrait information in the portrait information set; The assignment information corresponding to the second object is determined according to the assignment information of the first object corresponding to each first portrait information in the portrait information set.

10. The method according to claim 9, wherein: The determining, according to the assignment information of the first object corresponding to each first portrait information in the portrait information set, the assignment information corresponding to the second object comprises: The assignment information corresponding to the second object is determined according to the assignment information of the first object of each first portrait information in the portrait information set and the following formula: N=∑NWi*Ni*Ei / ∑Ni Among them, N is the assignment information corresponding to the second object, NWi is the assignment information of the first object corresponding to the i-th first portrait information in the portrait information set, Ni is the number of voice feature information corresponding to the i-th first portrait information, and Ei is the credibility information corresponding to the i-th first portrait information.

11. The method according to claim 10, wherein: Ei is positively correlated with Ni.

12. The method according to claim 9, wherein: For each portrait information set in the one or more portrait information sets, determining the second object corresponding to the portrait information set according to the first object corresponding to each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship contains the first object of each first portrait information in the portrait information set, including: For each portrait information set in the one or more portrait information sets, if the total number of first portrait information in the portrait information set exceeds a predetermined quantity threshold, determine the second object corresponding to the portrait information set according to the first object of each first portrait information in the portrait information set, wherein the set corresponding to the second object in the set relationship contains the first object of each first portrait information in the portrait information set; otherwise, The first objects of each first portrait information in the portrait information set are directly recorded as the second objects corresponding to the portrait information set.

13. The method according to any one of claims 1 to 12, wherein: The method further comprises: Update the historical second portrait information according to the second portrait information and the historical second portrait information corresponding to the user.

14. A computer device for obtaining target user portrait information, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 13.

15. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 13 are implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 13 are implemented.

Images